gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-07-31 22:04:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update and rerun pre-commit hooks for better code quality (#179)

Browse Source
This commit is contained in:
Xuehai Pan
2022-12-04 22:24:02 +08:00
committed by GitHub
parent 9157a97c80
commit 7e88559763
185 changed files with 1425 additions and 764 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.github/ISSUE_TEMPLATE/question.yml vendored
View File

@@ -12,7 +12,6 @@ body:
Basic questions that are not bugs or feature requests will be closed without reply, because GitHub
issues are not an appropriate venue for these. Advanced/nontrivial questions, especially in areas where
documentation is lacking, are very much welcome.
- type: textarea
id: question
attributes:

1
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@@ -14,6 +14,7 @@ Please delete options that are not relevant.
- [ ] This change requires a documentation update
### Screenshots
Please attach before and after screenshots of the change if applicable.
<!--

4
.gitignore vendored
View File

@@ -4,13 +4,17 @@
.DS_Store
.cache
.pytest_cache/
__pycache__/
# Setuptools distribution and build folders.
/dist/
/build
/wheels
/wheelhouse
# Virtualenv
/env
/venv
# Python egg metadata, regenerated from source files by setuptools.
/*.egg-info

40
.pre-commit-config.yaml
View File

@@ -1,17 +1,30 @@
---
# See https://pre-commit.com for more information
# See https://pre-commit.com/hooks.html for more hooks
repos:
- repo: https://github.com/python/black
rev: 22.3.0
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.4.0
hooks:
- id: black
- id: check-symlinks
- id: destroyed-symlinks
- id: trailing-whitespace
- id: end-of-file-fixer
- id: check-yaml
- id: check-toml
- id: check-ast
- id: check-added-large-files
- id: check-merge-conflict
- id: check-executables-have-shebangs
- id: check-shebang-scripts-are-executable
- id: detect-private-key
- id: debug-statements
- repo: https://github.com/codespell-project/codespell
rev: v2.1.0
rev: v2.2.2
hooks:
- id: codespell
args:
- --ignore-words-list=nd,reacher,thist,ths, ure, referenc,wile
- repo: https://github.com/PyCQA/flake8
rev: 4.0.1
rev: 6.0.0
hooks:
- id: flake8
args:
@@ -21,11 +34,19 @@ repos:
- --max-line-length=456
- --show-source
- --statistics
- repo: https://github.com/asottile/pyupgrade
rev: v3.3.0
hooks:
- id: pyupgrade
args: ["--py37-plus"]
- repo: https://github.com/PyCQA/isort
rev: 5.10.1
hooks:
- id: isort
args: ["--profile", "black"]
- repo: https://github.com/python/black
rev: 22.10.0
hooks:
- id: black
- repo: https://github.com/pycqa/pydocstyle
rev: 6.1.1
hooks:
@@ -36,11 +57,6 @@ repos:
- --explain
- --convention=google
additional_dependencies: ["toml"]
- repo: https://github.com/asottile/pyupgrade
rev: v2.32.0
hooks:
- id: pyupgrade
args: ["--py37-plus"]
- repo: local
hooks:
- id: pyright

1
CODE_OF_CONDUCT.rst
View File

@@ -65,4 +65,3 @@ Attribution
-----------
This Code of Conduct is adapted from `Python's Code of Conduct <https://www.python.org/psf/conduct/>`_, which is under a `Creative Commons License
<https://creativecommons.org/licenses/by-sa/3.0/>`_.

13
CONTRIBUTING.md
View File

@@ -12,9 +12,11 @@ Notably, we are not accepting these forms of contributions:
- New environments
# Development
This section contains technical instructions & hints for the contributors.
## Type checking
The project uses `pyright` to check types.
To type check locally, install `pyright` per official [instructions](https://github.com/microsoft/pyright#command-line).
It's configuration lives within `pyproject.toml`. It includes list of included and excluded files currently supporting type checks.
@@ -22,12 +24,15 @@ To run `pyright` for the project, run the pre-commit process (`pre-commit run --
Alternatively, pyright is a built-in feature of VSCode that will automatically provide type hinting.
### Adding typing to more modules and packages
If you would like to add typing to a module in the project,
the list of included, excluded and strict files can be found in pyproject.toml (pyproject.toml -> [tool.pyright]).
To run `pyright` for the project, run the pre-commit process (`pre-commit run --all-files`) or `pyright`
## Git hooks
The CI will run several checks on the new code pushed to the Gymnasium repository. These checks can also be run locally without waiting for the CI by following the steps below:
1. [install `pre-commit`](https://pre-commit.com/#install),
2. Install the Git hooks by running `pre-commit install`.
@@ -39,6 +44,7 @@ Additionally, for pull requests, the project runs a number of tests for the whol
These tests can be run locally with `pytest` in the root folder.
## Docstrings
Pydocstyle has been added to the pre-commit process such that all new functions follow the [google docstring style](https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html).
All new functions require either a short docstring, a single line explaining the purpose of a function
or a multiline docstring that documents each argument and the return type (if there is one) of the function.
@@ -49,14 +55,19 @@ To check your docstrings are correct, run `pre-commit run --all-files` or `pydoc
If all docstrings that fail, the source and reason for the failure is provided.
## Building the docs
Make sure that you have install the requirements:
```shell
cd docs
pip install -r requirements.txt
```
Then run
```
```shell
python scripts/gen_mds.py
make dirhtml
```
Now, navigate to `_build/dirhtml` and open `index.html` in your browser.

5
README.md
View File

@@ -4,12 +4,10 @@
<img src="https://raw.githubusercontent.com/Farama-Foundation/Gymnasium/main/gymnasium-text.png" width="500px"/>
</p>
Gymnasium is an open source Python library for developing and comparing reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. This is a fork of OpenAI's [Gym](https://github.com/openai/gym) library by the maintainers (OpenAI handed over maintenance a few years ago to an outside team), and is where future maintenance will occur going forward
The documentation website is at [gymnasium.farama.org](https://gymnasium.farama.org), and we have a public discord server (which we also use to coordinate development work) that you can join here: https://discord.gg/bnJ6kubTg6
## Environments
Gymnasium includes the following families of environments along with a wide variety of third-party environments
@@ -20,7 +18,6 @@ Gymnasium includes the following families of environments along with a wide vari
* [Atari](https://gymnasium.farama.org/environments/atari/) - A set of 57 Atari 2600 environments simulated through Stella and the Arcade Learning Environment that have a high range of complexity for agents to learn.
* [Third-party](https://gymnasium.farama.org/environments/third_party_environments/) - A number of environments have been created that are compatible with the Gymnasium API. Be aware of the version that the software was created for and use the `apply_env_compatibility` in `gymnasium.make` if necessary.
## Installation
To install the base Gymnasium library, use `pip install gymnasium`
@@ -59,8 +56,6 @@ Please note that this is an incomplete list, and just includes libraries that th
Gymnasium keeps strict versioning for reproducibility reasons. All environments end in a suffix like "\_v0". When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion. These inherent from Gym.
## Development Roadmap
We have a roadmap for future development work for Gymnasium available here: https://github.com/Farama-Foundation/Gymnasium/issues/12

5
docs/api/experimental.md
View File

@@ -28,6 +28,7 @@ Gymnasium already contains a large collection of wrappers, but we believe that t
* In v28, we aim to rewrite the VectorEnv to not inherit from Env, as a result new vectorised versions of the wrappers will be provided.
### Lambda Observation Wrappers
```{eval-rst}
.. py:currentmodule:: gymnasium
@@ -97,6 +98,7 @@ Gymnasium already contains a large collection of wrappers, but we believe that t
```
### Lambda Action Wrappers
```{eval-rst}
.. py:currentmodule:: gymnasium
@@ -130,6 +132,7 @@ Gymnasium already contains a large collection of wrappers, but we believe that t
```
### Lambda Reward Wrappers
```{eval-rst}
.. py:currentmodule:: gymnasium
@@ -154,6 +157,7 @@ Gymnasium already contains a large collection of wrappers, but we believe that t
```
### Common Wrappers
```{eval-rst}
.. py:currentmodule:: gymnasium
@@ -193,6 +197,7 @@ Gymnasium already contains a large collection of wrappers, but we believe that t
```
### Vector Only Wrappers
```{eval-rst}
.. py:currentmodule:: gymnasium

1
docs/api/registry.md
View File

@@ -30,7 +30,6 @@ This will not include environments registered only in OpenAI Gym however can be
.. autofunction:: gymnasium.spec
```
## Pretty print registry
```{eval-rst}

2
docs/api/spaces.md
View File

@@ -2,7 +2,6 @@
title: Spaces
---
# Spaces
```{toctree}
@@ -18,6 +17,7 @@ spaces/vector_utils
```
## The Base Class
```{eval-rst}
.. autoclass:: gymnasium.spaces.Space
```

2
docs/api/wrappers/action_wrappers.md
View File

@@ -9,8 +9,8 @@
```
## Available Action Wrappers
```{eval-rst}
.. autoclass:: gymnasium.wrappers.ClipAction
.. autoclass:: gymnasium.wrappers.RescaleAction
```

1
docs/api/wrappers/misc_wrappers.md
View File

@@ -1,4 +1,5 @@
# Misc Wrappers
```{eval-rst}
.. autoclass:: gymnasium.wrappers.AtariPreprocessing
.. autoclass:: gymnasium.wrappers.AutoResetWrapper

1
docs/conf.py
View File

@@ -22,6 +22,7 @@ from furo import gen_tutorials
import gymnasium
project = "Gymnasium"
copyright = "2022 Farama Foundation"
author = "Farama Foundation"

2
docs/content/migration-guide.md
View File

@@ -15,6 +15,7 @@ For more information, see the `guide </content/gym_compatibility>`_
```
### Example code for v21
```python
import gym
env = gym.make("LunarLander-v2", options={})
@@ -32,6 +33,7 @@ env.close()
```
### Example code for v26
```python
import gym
env = gym.make("LunarLander-v2", render_mode="human")

7
docs/environments/atari.md
View File

@@ -121,16 +121,20 @@ the arguments `difficulty` and `mode` when constructing the environment. This do
action spaces of default flavor choices.
## Observation Space
The observation issued by an Atari environment may be:
- the RGB image that is displayed to a human player,
- a grayscale version of that image or
- the state of the 128 Bytes of RAM of the console.
## Rewards
The exact reward dynamics depend on the environment and are usually documented in the game's manual. You can
find these manuals on [AtariAge](https://atariage.com/).
## Stochasticity
It was pointed out in [[1]](#1) that Atari games are entirely deterministic. Thus, agents could achieve
state-of-the-art performance by simply memorizing an optimal sequence of actions while completely ignoring observations from the environment.
To avoid this, ALE implements sticky actions: Instead of always simulating the action passed to the environment, there is a small
@@ -143,6 +147,7 @@ repeated `frameskip` many times. Otherwise, if `frameskip` is a tuple, the numbe
random between `frameskip[0]` (inclusive) and `frameskip[1]` (exclusive) in each environment step.
## Common Arguments
When initializing Atari environments via `gymnasium.make`, you may pass some additional arguments. These work for any
Atari environment. However, legal values for `mode` and `difficulty` depend on the environment.
@@ -170,6 +175,7 @@ action space will be reduced to a subset.
> This will guarantee proper scaling, audio support, and proper framerates
## Version History and Naming Schemes
All Atari games are available in three versions. They differ in the default settings of the arguments above.
The differences are listed in the following table:
@@ -204,6 +210,7 @@ are in the "ALE" namespace. The suffix "-ram" is still available. Thus, we get t
| ALE/Amidar-ram-v5 | `"ram"` | `5` | `0.25` | `True` |
## Flavors
Some games allow the user to set a difficulty level and a game mode. Different modes/difficulties may have different
game dynamics and (if a reduced action space is used) different action spaces. We follow the convention of [[2]](#2) and
refer to the combination of difficulty level and game mode as a flavor of a game. The following table shows

8
docs/environments/atari/adventure.md
View File

@@ -21,22 +21,27 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Adventure-v5")` |
## Description
You must find the enchanted chalice and return it to the golden castle. You can pick up various objects (keys, a sword,
a bridge, or a magnet) and have to fight or outmanoeuvre dragons.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -50,7 +55,7 @@ via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Adventure-v5")
```
@@ -68,6 +73,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Adventure-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

9
docs/environments/atari/air_raid.md
View File

@@ -20,10 +20,12 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/AirRaid-v5")` |
## Description
You control a ship that can move sideways. You must protect two buildings (one on the right and one on the left side of the screen) from
flying saucers that are trying to drop bombs on them.
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -40,12 +42,15 @@ flavor looks like this:
| 5 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -56,9 +61,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/AirRaid-v5")
```
@@ -76,6 +82,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("AirRaid-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/alien.md
View File

@@ -20,23 +20,28 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Alien-v5")` |
## Description
You are stuck in a maze-like space ship with three aliens. You goal is to destroy their eggs that are scattered
all over the ship while simultaneously avoiding the aliens (they are trying to kill you). You have a flamethrower that can help you turn
them away in tricky situations. Moreover, you can occasionally collect a power-up (pulsar) that gives you the temporary ability to kill aliens.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=815).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -48,14 +53,15 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points by destroying eggs, killing aliens, using pulsars, and collecting special prizes. When you are caught
by an alien, you will lose one of your lives. The number of lives you have depends on the game flavor. For a
table of scores corresponding to the different achievements, consult [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=815).
## Arguments
```
```python
env = gymnasium.make("ALE/Alien-v5")
```
@@ -67,13 +73,13 @@ A flavor is a combination of a game mode and a difficulty setting.
|-------------|---------------|--------------------|--------------|
| Alien | `[0, ..., 3]` | `[0, ..., 3]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Alien-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/amidar.md
View File

@@ -20,18 +20,19 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Amidar-v5")` |
## Description
This game is similar to Pac-Man: You are trying to visit all places on a 2-dimensional grid while simultaneously avoiding
your enemies. You can turn the tables at one point in the game: Your enemies turn into chickens and you can
catch them. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=817).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
flavor looks like this:
| Num | Action |
|-----|-----------|
| 0 | NOOP |
@@ -44,13 +45,17 @@ flavor looks like this:
| 7 | RIGHTFIRE |
| 8 | LEFTFIRE |
| 9 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -62,13 +67,14 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points by traversing new parts of the grid. Coloring an entire box in the maze or catching chickens gives extra points.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=817).
## Arguments
```
```python
env = gymnasium.make("ALE/Amidar-v5")
```
@@ -86,6 +92,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Amidar-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/assault.md
View File

@@ -1,6 +1,7 @@
---
title: Assault
---
# Assault
```{figure} ../../_static/videos/atari/assault.gif
@@ -19,10 +20,12 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Assault-v5")` |
## Description
You control a vehicle that can move sideways. A big mother ship circles overhead and continually deploys smaller drones.
You must destroy these enemies and dodge their attacks. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=827).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -38,13 +41,17 @@ flavor looks like this:
| 4 | LEFT |
| 5 | RIGHTFIRE |
| 6 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -55,9 +62,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Assault-v5")
```
@@ -67,13 +75,13 @@ The various ways to configure the environment are described in detail in the art
|-------------|-------------|--------------------|--------------|
| Assault | `[0]` | `[0]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Assault-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/asterix.md
View File

@@ -1,6 +1,7 @@
---
title: Asterix
---
# Asterix
```{figure} ../../_static/videos/atari/asterix.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Asterix-v5")` |
## Description
You are Asterix and can move horizontally (continuously) and vertically (discretely). Objects
move horizontally across the screen: lyres and other (more useful) objects. Your goal is to guide
Asterix in such a way as to avoid lyres and collect as many other objects as possible. You score points by collecting
@@ -27,6 +29,7 @@ many points, you will be awarded additional points.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=3325).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -44,13 +47,17 @@ flavor looks like this:
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -63,10 +70,12 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
A table of scores awarded for collecting the different objects is provided on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=3325).
## Arguments
```
```python
env = gymnasium.make("ALE/Asterix-v5")
```
@@ -76,13 +85,13 @@ The various ways to configure the environment are described in detail in the art
|-------------|-------------|--------------------|--------------|
| Asterix | `[0]` | `[0]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Asterix-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/asteroids.md
View File

@@ -1,6 +1,7 @@
---
title: Asteroids
---
# Asteroids
```{figure} ../../_static/videos/atari/asteroids.gif
@@ -19,12 +20,14 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Asteroids-v5")` |
## Description
This is a well-known arcade game: You control a spaceship in an asteroid field and must break up asteroids by shooting
them. Once all asteroids are destroyed, you enter a new level and new asteroids will appear. You will occasionally
be attacked by a flying saucer.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=828&itemTypeID=HTMLMANUAL)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -48,14 +51,16 @@ flavor looks like this:
| 12 | UPRIGHTFIRE |
| 13 | UPLEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -68,12 +73,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points for destroying asteroids, satellites and UFOs. The smaller the asteroid, the more points you score
for destroying it.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=828&itemTypeID=HTMLMANUAL).
## Arguments
```
```python
env = gymnasium.make("ALE/Asteroids-v5")
```
@@ -91,6 +98,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Asteroids-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/atlantis.md
View File

@@ -20,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Atlantis-v5")` |
## Description
Your job is to defend the submerged city of Atlantis. Your enemies slowly descend towards the city and you must
destroy them before they reach striking distance. To this end, you control three defense posts.
You lose if your enemies manage to destroy all seven of Atlantis' installations. You may rebuild installations
@@ -27,6 +28,7 @@ after you have fought of a wave of enemies and scored a sufficient number of poi
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=835).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -39,13 +41,17 @@ flavor looks like this:
| 1 | FIRE |
| 2 | RIGHTFIRE |
| 3 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -57,14 +63,15 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points for destroying enemies, keeping installations protected during attack waves. You score more points
if you manage to destroy your enemies with one of the outer defense posts.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=835).
## Arguments
```
```python
env = gymnasium.make("ALE/Atlantis-v5")
```
@@ -82,6 +89,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Amidar-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/bank_heist.md
View File

@@ -1,6 +1,7 @@
---
title: Bank Heist
---
# Bank Heist
```{figure} ../../_static/videos/atari/bank_heist.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/BankHeist-v5")` |
## Description
You are a bank robber and (naturally) want to rob as many banks as possible. You control your getaway car and must
navigate maze-like cities. The police chases you and will appear whenever you rob a bank. You may destroy police cars
by dropping sticks of dynamite. You can fill up your gas tank by entering a new city.
@@ -27,16 +29,21 @@ or run over the dynamite you have previously dropped.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1008).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -48,14 +55,15 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points for robbing banks and destroying police cars. If you rob nine or more banks, and then leave the city,
you will score extra points.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1008).
## Arguments
```
```python
env = gymnasium.make("ALE/BankHeist-v5")
```
@@ -73,6 +81,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("BankHeist-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

10
docs/environments/atari/battle_zone.md
View File

@@ -20,24 +20,28 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/BattleZone-v5")` |
## Description
You control a tank and must destroy enemy vehicles. This game is played in a first-person perspective and creates
a 3D illusion. A radar screen shows enemies around you. You start with 5 lives and gain up to 2 extra lives if you reach
a sufficient score.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=859&itemTypeID=HTMLMANUAL)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -50,12 +54,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You receive points for destroying enemies.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=859&itemTypeID=HTMLMANUAL).
## Arguments
```
```python
env = gymnasium.make("ALE/BattleZone-v5")
```
@@ -73,6 +78,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("BattleZone-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/beam_rider.md
View File

@@ -8,6 +8,7 @@ grid:
- Observation Low: 0
- Import: <code>gymnasium.make("ALE/BeamRider-v5")</code>
---
# Beam Rider
```{figure} ../../_static/videos/atari/beam_rider.gif
@@ -26,11 +27,13 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/BeamRider-v5")` |
## Description
You control a space-ship that travels forward at a constant speed. You can only steer it sideways between discrete
positions. Your goal is to destroy enemy ships, avoid their attacks and dodge space debris.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_thumbs.php?SystemID=2600&SoftwareID=860&itemTypeID=MANUAL)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -49,15 +52,16 @@ flavor looks like this:
| 7 | RIGHTFIRE |
| 8 | LEFTIFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -70,11 +74,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points for destroying enemies.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_thumbs.php?SystemID=2600&SoftwareID=860&itemTypeID=MANUAL).
## Arguments
```
```python
env = gymnasium.make("ALE/BeamRider-v5")
```
@@ -92,6 +98,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("BeamRider-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/berzerk.md
View File

@@ -1,6 +1,7 @@
---
title: Berzerk
---
# Berzerk
```{figure} ../../_static/videos/atari/berzerk.gif
@@ -19,23 +20,27 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Berzerk-v5")` |
## Description
You are stuck in a maze with evil robots. You must destroy them and avoid touching the walls of the maze, as this will kill you. You may be awarded extra lives after scoring a sufficient number of points, depending on the game mode.
You may also be chased by an undefeatable enemy, Evil Otto, that you must avoid. Evil Otto does not appear in the default mode.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=866&itemTypeID=HTMLMANUAL)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -48,11 +53,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points for destroying robots.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=866&itemTypeID=HTMLMANUAL).
## Arguments
```
```python
env = gymnasium.make("ALE/Berzerk-v5")
```
@@ -70,6 +77,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Berzerk-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/bowling.md
View File

@@ -1,6 +1,7 @@
---
title: Bowling
---
# Bowling
```{figure} ../../_static/videos/atari/bowling.gif
@@ -19,12 +20,14 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Bowling-v5")` |
## Description
Your goal is to score as many points as possible in the game of Bowling. A game consists of 10 frames and you have two
tries per frame. Knocking down all pins on the first try is called a "strike". Knocking down all pins on the second roll
is called a "spar". Otherwise, the frame is called "open".
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=879)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -40,14 +43,16 @@ flavor looks like this:
| 4 | UPFIRE |
| 5 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -60,13 +65,15 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You receive points for knocking down pins. The exact score depends on whether you manage a "strike", "spare" or "open"
frame. Moreover, the points you score for one frame may depend on following frames.
You can score up to 300 points in one game (if you manage to do 12 strikes).
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=879).
## Arguments
```
```python
env = gymnasium.make("ALE/Bowling-v5")
```
@@ -84,6 +91,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Bowling-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/boxing.md
View File

@@ -1,6 +1,7 @@
---
title: Boxing
---
# Boxing
```{figure} ../../_static/videos/atari/boxing.gif
@@ -19,21 +20,27 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Boxing-v5")` |
## Description
You fight an opponent in a boxing ring. You score points for hitting the opponent. If you score 100 points, your opponent is
knocked out.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=882).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -45,13 +52,14 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points by landing punches.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=882).
## Arguments
```
```python
env = gymnasium.make("ALE/Boxing-v5")
```
@@ -69,6 +77,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Boxing-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/breakout.md
View File

@@ -1,6 +1,7 @@
---
title: Breakout
---
# Breakout
```{figure} ../../_static/videos/atari/breakout.gif
@@ -19,12 +20,14 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Breakout-v5")` |
## Description
Another famous Atari game. The dynamics are similar to pong: You move a paddle and hit the ball in a brick wall at the
top of the screen. Your goal is to destroy the brick wall. You can try to break through the wall and let the ball
wreak havoc on the other side, all on its own! You have five lives.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=889).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -37,13 +40,17 @@ flavor looks like this:
| 1 | FIRE |
| 2 | RIGHT |
| 3 | LEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -55,13 +62,14 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points by destroying bricks in the wall. The reward for destroying a brick depends on the color of the brick.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=889).
## Arguments
```
```python
env = gymnasium.make("ALE/Breakout-v5")
```
@@ -79,6 +87,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Breakout-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

14
docs/environments/atari/carnival.md
View File

@@ -1,6 +1,7 @@
---
title: Carnival
---
# Carnival
```{figure} ../../_static/videos/atari/carnival.gif
@@ -19,19 +20,20 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Carnival-v5")` |
## Description
This is a "shoot 'em up" game. Targets move horizontally across the screen and you must shoot them. You are
in control of a gun that can be moved horizontally. The supply of ammunition is limited and chickens may steal some bullets
from you if you don't hit them in time.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=908).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
flavor looks like this:
| Num | Action |
|-----|-----------|
| 0 | NOOP |
@@ -40,13 +42,17 @@ flavor looks like this:
| 3 | LEFT |
| 4 | RIGHTFIRE |
| 5 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -58,14 +64,15 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points by destroying targets. Points (or bullets) may be subtracted if you hit the target when it shows a minus sign.
You will score extra points if it shows a plus sign!
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=908).
## Arguments
```
```python
env = gymnasium.make("ALE/Carnival-v5")
```
@@ -83,6 +90,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Carnival-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/centipede.md
View File

@@ -1,6 +1,7 @@
---
title: Centipede
---
# Centipede
```{figure} ../../_static/videos/atari/centipede.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Centipede-v5")` |
## Description
You are an elf and must use your magic wands to fend off spiders, fleas and centipedes. Your goal is to protect mushrooms in
an enchanted forest. If you are bitten by a spider, flea or centipede, you will be temporally paralyzed and you will
lose a magic wand. The game ends once you have lost all wands. You may receive additional wands after scoring
@@ -26,18 +28,21 @@ a sufficient number of points.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=911).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -50,13 +55,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points by hitting centipedes, scorpions, fleas and spiders. Additional points are awarded after every round
(i.e. after you have lost a wand) for mushrooms that were not destroyed.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=911).
## Arguments
```
```python
env = gymnasium.make("ALE/Centipede-v5")
```
@@ -74,6 +80,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Centipede-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

10
docs/environments/atari/chopper_command.md
View File

@@ -1,6 +1,7 @@
---
title: Chopper Command
---
# Chopper Command
```{figure} ../../_static/videos/atari/chopper_command.gif
@@ -19,22 +20,27 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/ChopperCommand-v5")` |
## Description
You control a helicopter and must protect truck convoys. To that end, you need to shoot down enemy aircraft.
A mini-map is displayed at the bottom of the screen.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=921).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -47,13 +53,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points by destroying planes and other helicopters. You score extra points at the end of every wave, depending on the number
of trucks that have survived.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=921).
## Arguments
```
```python
env = gymnasium.make("ALE/ChopperCommand-v5")
```
@@ -71,6 +78,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("ChopperCommand-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/crazy_climber.md
View File

@@ -1,6 +1,7 @@
---
title: Crazy Climber
---
# Crazy Climber
```{figure} ../../_static/videos/atari/crazy_climber.gif
@@ -19,16 +20,17 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/CrazyClimber-v5")` |
## Description
You are a climber trying to reach the top of four builidings, while avoiding obstacles like closing
windows and falling objects. When you receive damage (windows closing or objects) you will fall and
lose one life; you have a total of 5 lives before the end games. At the top of each building, there's
a helicopter which you need to catch to get to the next building. The goal is to climb as fast as
possible while receiving the least amount of damage.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=113).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -46,13 +48,17 @@ flavor looks like this:
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -65,10 +71,12 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
A table of scores awarded for completing each row of a building is provided on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=113).
## Arguments
```
```python
env = gymnasium.make("ALE/CrazyClimber-v5")
```
@@ -86,6 +94,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("CrazyClimber-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

10
docs/environments/atari/defender.md
View File

@@ -20,25 +20,29 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Defender-v5")` |
## Description
Aliens attack the earth. You control a spaceship and must defend humanity by destroying alien ships and rescuing humanoids.
You have three lives and three smart bombs. You lose a live when you are shot down by an alien spaceship.
Points are scored by destroying enemies and retrieving humans that are being abducted. You have an unlimited number of
laser missiles.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=128)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -51,12 +55,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You receive points for destroying enemies, rescuing abducted humans and keeping humans alive.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=128).
## Arguments
```
```python
env = gymnasium.make("ALE/Defender-v5")
```
@@ -74,6 +79,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Defender-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/demon_attack.md
View File

@@ -1,6 +1,7 @@
---
title: Demon Attack
---
# Demon Attack
```{figure} ../../_static/videos/atari/demon_attack.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/DemonAttack-v5")` |
## Description
You are facing waves of demons in the ice planet of Krybor. Points are accumulated by destroying
demons. You begin with 3 reserve bunkers, and can increase its number (up to 6) by avoiding enemy
attacks. Each attack wave you survive without any hits, grants you a new bunker. Every time an enemy
@@ -28,6 +30,7 @@ the game ends.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=135).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -45,13 +48,17 @@ flavor looks like this:
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -64,12 +71,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
Each enemy you slay gives you points. The amount of points depends on the type of demon and which
wave you are in. A detailed table of scores is provided on [the AtariAge
page](https://atariage.com/manual_html_page.php?SoftwareLabelID=135).
## Arguments
```
```python
env = gymnasium.make("ALE/DemonAttack-v5")
```
@@ -87,6 +96,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("DemonAttack-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/double_dunk.md
View File

@@ -1,6 +1,7 @@
---
title: Double Dunk
---
# Double Dunk
```{figure} ../../_static/videos/atari/double_dunk.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/DoubleDunk-v5")` |
## Description
You are playing a 2v2 game of basketball. At the start of each possession, you select between a set
of different plays and then execute them to either score or prevent your rivals from scoring. The
game lasts a set amount of time or until one of the teams reaches a certain score
@@ -26,6 +28,7 @@ game lasts a set amount of time or until one of the teams reaches a certain scor
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=153).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -43,13 +46,17 @@ flavor looks like this:
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -62,12 +69,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
Scores follow the rules of basketball. You can get either 3 points, 2 points foul line) depending
from where you shoot. After a defensive foul, a successful shot from the foul line gives you 1
point.
## Arguments
```
```python
env = gymnasium.make("ALE/DoubleDunk-v5")
```
@@ -85,6 +94,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("DoubleDunk-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/elevator_action.md
View File

@@ -1,6 +1,7 @@
---
title: Elevator Action
---
# Elevator Action
```{figure} ../../_static/videos/atari/elevator_action.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/ElevatorAction-v5")` |
## Description
You are a secret agent that must retrieve some secret documents and reach the ground level of a
building by going down an elevator/stairs. Once you reach the ground level, you are picked up and
taken to the next level. You are equipped with a gun to defend yourself against enemy agents waiting
@@ -29,6 +31,7 @@ This is an unreleased prototype based on the arcade game. Limited documentation
page](https://atariage.com/manual_thumbs.php?SoftwareLabelID=1131).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -46,13 +49,17 @@ flavor looks like this:
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -65,12 +72,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You start with 4 lives and are awarded 100 points for each enemy shot, and 500 points for each
secret document collected (visiting a red door). Each time you get shot you lose one life and the
game ends when losing all lives.
## Arguments
```
```python
env = gymnasium.make("ALE/ElevatorAction-v5")
```
@@ -88,6 +97,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("ElevatorAction-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/enduro.md
View File

@@ -1,6 +1,7 @@
---
title: Enduro
---
# Enduro
```{figure} ../../_static/videos/atari/enduro.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Enduro-v5")` |
## Description
You are a racer in the National Enduro, a long-distance endurance race. You must overtake a certain
amount of cars each day to stay on the race. The first day you need to pass 200 cars, and 300 for
each following day. The game ends if you do not meet your overtake quota for the day.
@@ -26,6 +28,7 @@ each following day. The game ends if you do not meet your overtake quota for the
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=163).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -43,13 +46,17 @@ flavor looks like this:
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -62,10 +69,12 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You get 1 point for each vehicle you overtake.
## Arguments
```
```python
env = gymnasium.make("ALE/Enduro-v5")
```
@@ -83,6 +92,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Enduro-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

15
docs/environments/atari/fishing_derby.md
View File

@@ -1,6 +1,7 @@
---
title: FishingDerby
---
# FishingDerby
```{figure} ../../_static/videos/atari/fishing_derby.gif
@@ -19,15 +20,18 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/FishingDerby-v5")` |
## Description
your objective is to catch more sunfish than your opponent. But it's not just between you and the other fisherman, as a big, black shark is lurking just below the surface, waiting to steal your catch! Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=182).
### Rewards
The exact reward dynamics depend on the environment and are usually documented in the game's manual. You can
find these manuals on [AtariAge](https://atariage.com/manual_html_page.php?SoftwareLabelID=182).
Atari environments are simulated via the Arcade Learning Environment (ALE) [[1]](#1).
### Action Space
The action space a subset of the following discrete set of legal actions:
| Num | Action |
@@ -58,13 +62,17 @@ legal space by passing the keyword argument `full_action_space=True` to `make`.
The reduced action space of an Atari environment may depend on the flavor of the game. You can specify the flavor by providing
the arguments `difficulty` and `mode` when constructing the environment. This documentation only provides details on the
action spaces of default flavors.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -75,9 +83,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/FishingDerby-v5")
```
@@ -87,13 +96,13 @@ The various ways to configure the environment are described in detail in the art
|--------------|-------------|--------------------|--------------|
| FishingDerby | `[0]` | `[0, ..., 3]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("FishingDerby-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

16
docs/environments/atari/freeway.md
View File

@@ -1,6 +1,7 @@
---
title: Freeway
---
# Freeway
```{figure} ../../_static/videos/atari/freeway.gif
@@ -19,15 +20,18 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Freeway-v5")` |
## Description
your objective is to guide your chicken across lane after lane of busy rush hour traffic. You receive a point for every chicken that makes it to the top of the screen after crossing all the lanes of traffic. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_thumbs.php?SoftwareLabelID=192).
### Rewards
The exact reward dynamics depend on the environment and are usually documented in the game's manual. You can
find these manuals on [AtariAge](https://atariage.com/manual_thumbs.php?SoftwareLabelID=192).
Atari environments are simulated via the Arcade Learning Environment (ALE) [[1]](#1).
### Action Space
The action space a subset of the following discrete set of legal actions:
| Num | Action |
@@ -58,13 +62,17 @@ legal space by passing the keyword argument `full_action_space=True` to `make`.
The reduced action space of an Atari environment may depend on the flavor of the game. You can specify the flavor by providing
the arguments `difficulty` and `mode` when constructing the environment. This documentation only provides details on the
action spaces of default flavors.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -75,9 +83,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Freeway-v5")
```
@@ -87,14 +96,13 @@ The various ways to configure the environment are described in detail in the art
|-------------|---------------|--------------------|--------------|
| Freeway | `[0, ..., 7]` | `[0, 1]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Freeway-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

16
docs/environments/atari/frostbite.md
View File

@@ -1,6 +1,7 @@
---
title: Frostbite
---
# Frostbite
```{figure} ../../_static/videos/atari/frostbite.gif
@@ -19,15 +20,18 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Frostbite-v5")` |
## Description
In Frostbite, the player controls "Frostbite Bailey" who hops back and forth across across an Arctic river, changing the color of the ice blocks from white to blue. Each time he does so, a block is added to his igloo. [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=199).
### Rewards
The exact reward dynamics depend on the environment and are usually documented in the game's manual. You can
find these manuals on [AtariAge](https://atariage.com/manual_html_page.php?SoftwareLabelID=199).
Atari environments are simulated via the Arcade Learning Environment (ALE) [[1]](#1).
### Action Space
The action space a subset of the following discrete set of legal actions:
| Num | Action |
@@ -58,13 +62,17 @@ legal space by passing the keyword argument `full_action_space=True` to `make`.
The reduced action space of an Atari environment may depend on the flavor of the game. You can specify the flavor by providing
the arguments `difficulty` and `mode` when constructing the environment. This documentation only provides details on the
action spaces of default flavors.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -75,9 +83,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Frostbite-v5")
```
@@ -87,14 +96,13 @@ The various ways to configure the environment are described in detail in the art
|-------------|-------------|--------------------|--------------|
| Frostbite | `[0, 2]` | `[0]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Frostbite-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

16
docs/environments/atari/gopher.md
View File

@@ -1,6 +1,7 @@
---
title: Gopher
---
# Gopher
```{figure} ../../_static/videos/atari/gopher.gif
@@ -19,15 +20,18 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Gopher-v5")` |
## Description
The player controls a shovel-wielding farmer who protects a crop of three carrots from a gopher. [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=218).
### Rewards
The exact reward dynamics depend on the environment and are usually documented in the game's manual. You can
find these manuals on [AtariAge](https://atariage.com/manual_html_page.php?SoftwareLabelID=218).
Atari environments are simulated via the Arcade Learning Environment (ALE) [[1]](#1).
### Action Space
The action space a subset of the following discrete set of legal actions:
| Num | Action |
@@ -58,13 +62,17 @@ legal space by passing the keyword argument `full_action_space=True` to `make`.
The reduced action space of an Atari environment may depend on the flavor of the game. You can specify the flavor by providing
the arguments `difficulty` and `mode` when constructing the environment. This documentation only provides details on the
action spaces of default flavors.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -75,9 +83,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Gopher-v5")
```
@@ -87,14 +96,13 @@ The various ways to configure the environment are described in detail in the art
|-------------|-------------|--------------------|--------------|
| Gopher | `[0, 2]` | `[0, 1]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Gopher-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

16
docs/environments/atari/gravitar.md
View File

@@ -1,6 +1,7 @@
---
title: Gravitar
---
# Gravitar
```{figure} ../../_static/videos/atari/gravitar.gif
@@ -19,15 +20,18 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Gravitar-v5")` |
## Description
The player controls a small blue spacecraft. The game starts in a fictional solar system with several planets to explore. If the player moves his ship into a planet, he will be taken to a side-view landscape. Player has to destroy red bunkers [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=223).
### Rewards
The exact reward dynamics depend on the environment and are usually documented in the game's manual. You can
find these manuals on [AtariAge](https://atariage.com/manual_html_page.php?SoftwareLabelID=223).
Atari environments are simulated via the Arcade Learning Environment (ALE) [[1]](#1).
### Action Space
The action space a subset of the following discrete set of legal actions:
| Num | Action |
@@ -58,13 +62,17 @@ legal space by passing the keyword argument `full_action_space=True` to `make`.
The reduced action space of an Atari environment may depend on the flavor of the game. You can specify the flavor by providing
the arguments `difficulty` and `mode` when constructing the environment. This documentation only provides details on the
action spaces of default flavors.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -75,9 +83,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Gravitar-v5")
```
@@ -87,14 +96,13 @@ The various ways to configure the environment are described in detail in the art
|-------------|---------------|--------------------|--------------|
| Gravitar | `[0, ..., 4]` | `[0]` | `0` |
You may use the suffix "-ram" to switch to the RAM observation space. In v0 and v4, the suffixes "Deterministic" and "NoFrameskip"
are available. These are no longer supported in v5. In order to obtain equivalent behavior, pass keyword arguments to `gymnasium.make` as outlined in
the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Gravitar-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

10
docs/environments/atari/hero.md
View File

@@ -20,25 +20,29 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Hero-v5")` |
## Description
You need to rescue miners that are stuck in a mine shaft. You have access to various tools: A propeller backpack that
allows you to fly wherever you want, sticks of dynamite that can be used to blast through walls, a laser beam to kill
vermin, and a raft to float across stretches of lava.
You have a limited amount of power. Once you run out, you lose a live.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=228)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -51,13 +55,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points for shooting critters, rescuing miners, and dynamiting walls.
Extra points are rewarded for any power remaining after rescuing a miner.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=228).
## Arguments
```
```python
env = gymnasium.make("ALE/Hero-v5")
```
@@ -75,6 +80,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Hero-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/ice_hockey.md
View File

@@ -1,6 +1,7 @@
---
title: IceHockey
---
# IceHockey
```{figure} ../../_static/videos/atari/ice_hockey.gif
@@ -19,23 +20,28 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/IceHockey-v5")` |
## Description
Your goal is to score as many points as possible in a standard game of Ice Hockey over a 3-minute time period. The ball is usually called "the puck".
There are 32 shot angles ranging from the extreme left to the extreme right. The angles can only aim towards the opponent's goal.
Just as in real hockey, you can pass the puck by shooting it off the sides of the rink. This can be really key when you're in position to score a goal.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=241)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -47,14 +53,15 @@ instead. The respective observation spaces are
respectively. [The general article on Atari environments](https://brosa.ca/blog/ale-release-v0.7) outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points by shooting the puck into your opponent's goal. Your opponent scores in the same manner.
There are no limits to how many points you can get per game, other than the time limit of 3-minute games.
For a more detailed documentation, consult [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=241).
## Arguments
```
```python
env = gymnasium.make("ALE/IceHockey-v5")
```
@@ -72,6 +79,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Icehockey-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/jamesbond.md
View File

@@ -1,6 +1,7 @@
---
title: Jamesbond
---
# Jamesbond
```{figure} ../../_static/videos/atari/jamesbond.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Jamesbond-v5")` |
## Description
Your mission is to control Mr. Bond's specially designed multipurpose craft to complete a variety of missions.
The craft moves forward with a right motion and slightly back with a left motion.
An up or down motion causes the craft to jump or dive.
@@ -26,17 +28,21 @@ You can also fire by either lobbing a bomb to the bottom of the screen or firing
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=250)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -48,14 +54,15 @@ instead. The respective observation spaces are
respectively. [The general article on Atari environments](https://brosa.ca/blog/ale-release-v0.7) outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
The game ends when you complete the last mission or when you lose the last craft. In either case, you'll receive your final score.
There will be a rating based on your score. The highest rating in NOVICE is 006. The highest rating in AGENT is 007.
For a more detailed documentation, consult [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=250).
## Arguments
```
```python
env = gymnasium.make("ALE/Jamesbond-v5")
```
@@ -73,6 +80,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Jamesbond-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

13
docs/environments/atari/journey_escape.md
View File

@@ -1,6 +1,7 @@
---
title: JourneyEscape
---
# JourneyEscape
```{figure} ../../_static/videos/atari/journey_escape.gif
@@ -19,11 +20,13 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/JourneyEscape-v5")` |
## Description
You must lead all 5 members of JOURNEY through waves of pesky characters and backstage obstacles to the Scarab Escape Vehicle before time runs out.
You must also protect $50,000 in concert cash from grasping groupies, photographers, and promoters.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=252)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -48,13 +51,17 @@ flavor looks like this:
| 15 | UPLEFTFIRE |
| 16 | DOWNRIGHTFIRE |
| 17 | DOWNLEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -66,14 +73,15 @@ instead. The respective observation spaces are
respectively. [The general article on Atari environments](https://brosa.ca/blog/ale-release-v0.7) outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
At the start of the game, you will have $50,000 and 60 units of time.
Your end game score with be dependent on how much time you have remaining and who you encounter along the way.
For a more detailed documentation, consult [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=252).
## Arguments
```
```python
env = gymnasium.make("ALE/JourneyEscape-v5")
```
@@ -91,6 +99,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("JourneyEscape-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/kangaroo.md
View File

@@ -1,6 +1,7 @@
---
title: Kangaroo
---
# Kangaroo
```{figure} ../../_static/videos/atari/kangaroo.gif
@@ -19,22 +20,27 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Kangaroo-v5")` |
## Description
The object of the game is to score as many points as you can while controlling Mother Kangaroo to rescue her precious baby. You start the game with three lives.
During this rescue mission, Mother Kangaroo encounters many obstacles. You need to help her climb ladders, pick bonus fruit, and throw punches at monkeys.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=923)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -46,14 +52,15 @@ instead. The respective observation spaces are
respectively. [The general article on Atari environments](https://brosa.ca/blog/ale-release-v0.7) outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
Your score will be shown at the top right corner of the game.
Your end game score with be dependent on how much time you have remaining and who you encounter along the way.
For a more detailed documentation, consult [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=923).
## Arguments
```
```python
env = gymnasium.make("ALE/Kangaroo-v5")
```
@@ -71,6 +78,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Kangaroo-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/krull.md
View File

@@ -1,6 +1,7 @@
---
title: Krull
---
# Krull
```{figure} ../../_static/videos/atari/krull.gif
@@ -19,22 +20,27 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Krull-v5")` |
## Description
Your mission is to find and enter the Beast's Black Fortress, rescue Princess Lyssa, and destroy the Beast.
The task is not an easy one, for the location of the Black Fortress changes with each sunrise on Krull.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=267)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -46,14 +52,15 @@ instead. The respective observation spaces are
respectively. [The general article on Atari environments](https://brosa.ca/blog/ale-release-v0.7) outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You will receive various scores for each monster you kill.
You can play the game until you have lost all your lives.
For a more detailed documentation, consult [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=267).
## Arguments
```
```python
env = gymnasium.make("ALE/Krull-v5")
```
@@ -71,6 +78,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Krull-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/kung_fu_master.md
View File

@@ -1,6 +1,7 @@
---
title: Kung Fu Master
---
# Kung Fu Master
```{figure} ../../_static/videos/atari/kung_fu_master.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/KungFuMaster-v5")` |
## Description
You are a Kung-Fu Master fighting your way through the Evil Wizard's temple. Your goal is to rescue Princess Victoria, defeating various enemies along the way. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_thumbs.php?SoftwareLabelID=268).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -40,13 +43,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 11 | UPLEFTFIRE |
| 12 | DOWNRIGHTFIRE |
| 13 | DOWNLEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -57,9 +64,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/KungFuMaster-v5")
```
@@ -75,6 +83,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("KungFuMaster-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/montezuma_revenge.md
View File

@@ -1,6 +1,7 @@
---
title: Montezuma Revenge
---
# Montezuma Revenge
```{figure} ../../_static/videos/atari/montezuma_revenge.gif
@@ -19,19 +20,25 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/MontezumaRevenge-v5")` |
## Description
Your goal is to acquire Montezuma's treasure by making your way through a maze of chambers within the emperor's fortress. You must avoid deadly creatures while collecting valuables and tools which can help you escape with the treasure. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=310).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions
will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -42,9 +49,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/MontezumaRevenge-v5")
```
@@ -60,6 +68,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("MontezumaRevenge-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/ms_pacman.md
View File

@@ -1,6 +1,7 @@
---
title: Ms Pacman
---
# Ms Pacman
```{figure} ../../_static/videos/atari/ms_pacman.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/MsPacman-v5")` |
## Description
Your goal is to collect all of the pellets on the screen while avoiding the ghosts.
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -35,13 +38,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 6 | UPLEFT |
| 7 | DOWNRIGHT |
| 8 | DOWNLEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -52,9 +59,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/MsPacman-v5")
```
@@ -70,10 +78,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("MsPacman-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

10
docs/environments/atari/name_this_game.md
View File

@@ -1,6 +1,7 @@
---
title: Name This Game
---
# Name This Game
```{figure} ../../_static/videos/atari/name_this_game.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/NameThisGame-v5")` |
## Description
Your goal is to defend the treasure that you have discovered. You must fight off a shark and an octopus while keeping an eye on your oxygen supply. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=323).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -34,12 +37,15 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 5 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -50,9 +56,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/NameThisGame-v5")
```
@@ -68,6 +75,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("NameThisGame-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/phoenix.md
View File

@@ -1,6 +1,7 @@
---
title: Phoenix
---
# Phoenix
```{figure} ../../_static/videos/atari/phoenix.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Phoenix-v5")` |
## Description
Your goal is to reach and shoot the alien pilot. On your way there, you must eliminate waves of war birds while avoiding their bombs. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_thumbs.php?SoftwareLabelID=355).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -34,13 +37,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 5 | RIGHTFIRE |
| 6 | LEFTFIRE |
| 7 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -51,9 +58,10 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Phoenix-v5")
```
@@ -69,6 +77,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Phoenix-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/pitfall.md
View File

@@ -1,6 +1,7 @@
---
title: Pitfall
---
# Pitfall
```{figure} ../../_static/videos/atari/pitfall.gif
@@ -19,19 +20,24 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Pitfall-v5")` |
## Description
You control Pitfall Harry and are tasked with collecting all the treasures in a jungle within 20 minutes. You have three lives. The game is over if you collect all the treasures or if you die or if the time runs out.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=360)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -44,11 +50,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You get score points for collecting treasure, you lose points through some misfortunes like falling down a hole.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=360).
## Arguments
```
```python
env = gymnasium.make("ALE/Pitfall-v5")
```
@@ -66,10 +74,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Pitfall-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

13
docs/environments/atari/pong.md
View File

@@ -1,6 +1,7 @@
---
title: Pong
---
# Pong
```{figure} ../../_static/videos/atari/pong.gif
@@ -19,10 +20,12 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Pong-v5")` |
## Description
You control the right paddle, you compete against the left paddle controlled by the computer. You each try to keep deflecting the ball away from your goal and into your opponent's goal.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=587)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
@@ -37,13 +40,15 @@ flavor looks like this:
| 4 | RIGHTFIRE |
| 5 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -56,11 +61,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You get score points for getting the ball to pass the opponent's paddle. You lose points if the ball passes your paddle.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=587).
## Arguments
```
```python
env = gymnasium.make("ALE/Pong-v5")
```
@@ -78,10 +85,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Pong-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

12
docs/environments/atari/pooyan.md
View File

@@ -1,6 +1,7 @@
---
title: Pooyan
---
# Pooyan
```{figure} ../../_static/videos/atari/pooyan.gif
@@ -24,6 +25,7 @@ You are a mother pig protecting her piglets (Pooyans) from wolves. In the first
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=372)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
@@ -37,12 +39,16 @@ flavor looks like this:
| 3 | DOWN |
| 4 | UPFIRE |
| 5 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -55,11 +61,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
If you hit a balloon, wolf or stone with an arrow you score points.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=372).
## Arguments
```
```python
env = gymnasium.make("ALE/Pooyan-v5")
```
@@ -77,10 +85,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Pooyan-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

12
docs/environments/atari/private_eye.md
View File

@@ -1,6 +1,7 @@
---
title: PrivateEye
---
# PrivateEye
```{figure} ../../_static/videos/atari/private_eye.gif
@@ -19,19 +20,24 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/PrivateEye-v5")` |
## Description
You control the French Private Eye Pierre Touche. Navigate the city streets, parks, secret passages, dead-ends and one-ways in search of the ringleader, Henri Le Fiend and his gang. You also need to find evidence and stolen goods that are scattered about. There are five cases, complete each case before its statute of limitations expires.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=376)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -44,11 +50,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points for completing your tasks like gathering evidence, nabbing questionable characters or closing cases etc. You lose points if you get hit or if your auto is on a pothole.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=376).
## Arguments
```
```python
env = gymnasium.make("ALE/PrivateEye-v5")
```
@@ -66,10 +74,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("PrivateEye-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

12
docs/environments/atari/qbert.md
View File

@@ -1,6 +1,7 @@
---
title: Qbert
---
# Qbert
```{figure} ../../_static/videos/atari/qbert.gif
@@ -19,10 +20,12 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Qbert-v5")` |
## Description
You are Q*bert. Your goal is to change the color of all the cubes on the pyramid to the pyramid's 'destination' color. To do this, you must hop on each cube on the pyramid one at a time while avoiding nasty creatures that lurk there.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=1224&itemTypeID=HTMLMANUAL)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
@@ -38,11 +41,14 @@ flavor looks like this:
| 5 | DOWN |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -55,11 +61,13 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
You score points for changing color of the cubes to their destination colors or by defeating enemies. You also gain points for completing a level.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SystemID=2600&SoftwareID=1224&itemTypeID=HTMLMANUAL).
## Arguments
```
```python
env = gymnasium.make("ALE/Qbert-v5")
```
@@ -77,10 +85,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Qbert-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

12
docs/environments/atari/riverraid.md
View File

@@ -1,6 +1,7 @@
---
title: Riverraid
---
# Riverraid
```{figure} ../../_static/videos/atari/riverraid.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Riverraid-v5")` |
## Description
You control a jet that flies over a river: you can move it sideways and fire missiles to destroy enemy objects. Each time an enemy object is destroyed you score points (i.e. rewards).
You lose a jet when you run out of fuel: fly over a fuel depot when you begin to run low.
@@ -30,14 +32,19 @@ The game begins with a squadron of three jets in reserve and you're given an add
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=409)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -50,6 +57,7 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
Score points are your only reward. You get score points each time you destroy an enemy object:
| Enemy Object | Score Points |
@@ -61,9 +69,10 @@ Score points are your only reward. You get score points each time you destroy an
| Bridge | 500 |
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=409).
## Arguments
```
```python
env = gymnasium.make("ALE/Riverraid-v5")
```
@@ -81,6 +90,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Riverraid-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/road_runner.md
View File

@@ -1,6 +1,7 @@
---
title: Road Runner
---
# Road Runner
```{figure} ../../_static/videos/atari/road_runner.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/RoadRunner-v0")` |
## Description
You control the Road Runner(TM) in a race; you can control the direction to run in and times to jumps.
The goal is to outrun Wile E. Coyote(TM) while avoiding the hazards of the desert.
@@ -33,14 +35,19 @@ destroying the coyote.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=412)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -53,6 +60,7 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
Score points are your only reward. You get score points each time you:
| actions | points |
@@ -63,9 +71,10 @@ Score points are your only reward. You get score points each time you:
| get the coyote hit by a truck | 1000 |
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=412).
## Arguments
```
```python
env = gymnasium.make("ALE/RoadRunner-v5")
```
@@ -83,6 +92,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("RoadRunner-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/robotank.md
View File

@@ -1,6 +1,7 @@
---
title: Robot Tank
---
# Robot Tank
```{figure} ../../_static/videos/atari/robotank.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Robotank-v0")` |
## Description
You control your Robot Tanks to destroy enemies and avoid enemy fire.
Game ends when all of your Robot Tanks are
@@ -35,14 +37,19 @@ You earn one bonus Robot Tank for every enemy squadron destroyed. The maximum
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=416)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -55,6 +62,7 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
The number of enemies destroyed is the only reward.
A small tank appears at the top of your screen for each enemy
@@ -62,9 +70,10 @@ A small tank appears at the top of your screen for each enemy
destroyed.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=416).
## Arguments
```
```python
env = gymnasium.make("ALE/Robotank-v5")
```
@@ -82,6 +91,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Robotank-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/seaquest.md
View File

@@ -1,6 +1,7 @@
---
title: Seaquest
---
# Seaquest
```{figure} ../../_static/videos/atari/seaquest.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Seaquest-v0")` |
## Description
You control a sub able to move in all directions and fire torpedoes.
The goal is to retrieve as many divers as you
can, while dodging and blasting enemy subs and killer sharks; points will be awarded accordingly.
@@ -38,14 +40,19 @@ to surface, with less than six divers, you lose one diver as well.
Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=424)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -58,6 +65,7 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
Score points are your only reward.
Blasting enemy sub and killer shark is worth
@@ -72,9 +80,10 @@ moment you surface. The more oxygen you have left, the more bonus points
you're given.
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=424).
## Arguments
```
```python
env = gymnasium.make("ALE/Seaquest-v5")
```
@@ -92,6 +101,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Seaquest-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/skiing.md
View File

@@ -1,6 +1,7 @@
---
title: Skiing
---
# Skiings
```{figure} ../../_static/videos/atari/skiing.gif
@@ -19,6 +20,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Skiing-v0")` |
## Description
You control a skier who can move sideways.
The goal is to run through all gates (between the poles) in the fastest time.
@@ -30,6 +32,7 @@ and keep going. But you do lose time, so be careful!
Detailed documentation can be found on [the AtariAge page [SLALOM RACING section]](https://atariage.com/manual_html_page.php?SoftwareLabelID=434)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend
@@ -41,13 +44,17 @@ flavor looks like this:
| 0 | NOOP |
| 1 | RIGHT |
| 2 | LEFT |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -60,12 +67,14 @@ respectively. The general article on Atari environments outlines different ways
via `gymnasium.make`.
### Rewards
Seconds are your only rewards - negative rewards and penalties (e.g. missing a gate) are assigned as additional seconds.
For a more detailed documentation, see [the AtariAge page [SLALOM RACING section]](https://atariage.com/manual_html_page.php?SoftwareLabelID=434).
## Arguments
```
```python
env = gymnasium.make("ALE/Skiing-v5")
```
@@ -83,6 +92,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Skiing-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

12
docs/environments/atari/solaris.md
View File

@@ -1,6 +1,7 @@
---
title: Solaris
---
# Solaris
```{figure} ../../_static/videos/atari/solaris.gif
@@ -19,17 +20,23 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Solaris-v5")` |
## Description
You control a spaceship. Blast enemies before they can blast you. You can warp to different sectors. You have to defend Federation planets, and destroy Zylon forces. Keep track of your fuel, if you run out you lose a life. Warp to a Federation planet to refuel. The game ends if all your ships are destroyed or if you reach the Solaris planet. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=450)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -44,9 +51,10 @@ via `gymnasium.make`.
### Rewards
You gain points for destroying enemies, rescuing cadets, making it through a corridor, destroying enemy planets etc. For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=450).
## Arguments
```
```python
env = gymnasium.make("ALE/Solaris-v5")
```
@@ -64,10 +72,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Solaris-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

10
docs/environments/atari/space_invaders.md
View File

@@ -1,6 +1,7 @@
---
title: SpaceInvaders
---
# SpaceInvaders
```{figure} ../../_static/videos/atari/space_invaders.gif
@@ -23,6 +24,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
Your objective is to destroy the space invaders by shooting your laser cannon at them before they reach the Earth. The game ends when all your lives are lost after taking enemy fire, or when they reach the earth. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=460)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
@@ -38,11 +40,14 @@ flavor looks like this:
| 5 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -57,9 +62,10 @@ via `gymnasium.make`.
### Rewards
You gain points for destroying space invaders. The invaders in the back rows are worth more points. For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=460).
## Arguments
```
```python
env = gymnasium.make("ALE/SpaceInvaders-v5")
```
@@ -77,10 +83,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("SpaceInvaders-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

9
docs/environments/atari/star_gunner.md
View File

@@ -1,6 +1,7 @@
---
title: StarGunner
---
# StarGunner
```{figure} ../../_static/videos/atari/star_gunner.gif
@@ -23,6 +24,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
Stop the alien invasion by shooting down alien saucers and creatures while avoiding bombs. More details can be found on [the Atari Mania page](http://www.atarimania.com/game-atari-2600-vcs-stargunner_16921.html)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
@@ -38,11 +40,14 @@ flavor looks like this:
| 5 | DOWN |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -60,7 +65,7 @@ You score points for destroying enemies. You get bonus points for clearing a wav
## Arguments
```
```python
env = gymnasium.make("ALE/StarGunner-v5")
```
@@ -78,10 +83,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("StarGunner-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

10
docs/environments/atari/tennis.md
View File

@@ -1,6 +1,7 @@
---
title: Tennis
---
# Tennis
```{figure} ../../_static/videos/atari/tennis.gif
@@ -24,15 +25,19 @@ You control the orange player playing against a computer-controlled blue player.
The first player to win at least 6 games with a margin of at least two games wins the match. If the score is tied at 6-6, the first player to go 2 games up wins the match. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=555)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
Even if you use v0 or v4 or specify `full_action_space=False` during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -47,9 +52,10 @@ via `gymnasium.make`.
### Rewards
The scoring is as per the sport of tennis, played till one set. For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=555).
## Arguments
```
```python
env = gymnasium.make("ALE/Tennis-v5")
```
@@ -67,10 +73,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Tennis-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

10
docs/environments/atari/time_pilot.md
View File

@@ -1,6 +1,7 @@
---
title: TimePilot
---
# TimePilot
```{figure} ../../_static/videos/atari/time_pilot.gif
@@ -23,6 +24,7 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
You control an aircraft. Use it to destroy your enemies. As you progress in the game, you encounter enemies with technology that is increasingly from the future. More details can be found on [the Atari Mania page](http://www.atarimania.com/game-atari-2600-vcs-time-pilot_8038.html)
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment.
However, if you use v0 or v4 or specify `full_action_space=False` during initialization, only a reduced
number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of `mode` and `difficulty`). The reduced action space for the default
@@ -42,11 +44,14 @@ flavor looks like this:
| 9 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -58,14 +63,13 @@ instead. The respective observation spaces are
respectively. The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
### Rewards
You score points for destroying enemies, gaining more points for difficult enemies. For a more detailed documentation, see [the Atari Mania page](http://www.atarimania.com/game-atari-2600-vcs-time-pilot_8038.html).
## Arguments
```
```python
env = gymnasium.make("ALE/TimePilot-v5")
```
@@ -82,10 +86,10 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("TimePilot-v0")`.
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.
* v5: Stickiness was added back and stochastic frameskipping was removed. The entire action space is used by default. The environments are now in the "ALE" namespace.
* v4: Stickiness of actions was removed
* v0: Initial versions release (1.0.0)

11
docs/environments/atari/tutankham.md
View File

@@ -1,6 +1,7 @@
---
title: Tutankham
---
# Tutankham
```{figure} ../../_static/videos/atari/tutankham.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Tutankham-v5")` |
## Description
Your goal is to rack up points by finding treasures in the mazes of the tomb while eliminating its guardians. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_thumbs.php?SoftwareLabelID=572).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -34,13 +37,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 5 | UPFIRE |
| 6 | RIGHTFIRE |
| 7 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -51,9 +58,10 @@ instead. The respective observation spaces are
The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Tutankham-v5")
```
@@ -69,6 +77,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Tutankham-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/up_n_down.md
View File

@@ -1,6 +1,7 @@
---
title: Up n' Down
---
# Up n' Down
```{figure} ../../_static/videos/atari/up_n_down.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/UpNDown-v5")` |
## Description
Your goal is to steer your baja bugger to collect prizes and eliminate opponents. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=574).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -32,13 +35,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 3 | DOWN |
| 4 | UPFIRE |
| 5 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -49,9 +56,10 @@ instead. The respective observation spaces are
The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/UpNDown-v5")
```
The various ways to configure the environment are described in detail in the article on Atari environments.
@@ -68,6 +76,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("UpNDown-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/venture.md
View File

@@ -1,6 +1,7 @@
---
title: Venture
---
# Venture
```{figure} ../../_static/videos/atari/venture.gif
@@ -19,17 +20,23 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Venture-v5")` |
## Description
Your goal is to capture the treasure in every chamber of the dungeon while eliminating the monsters. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=576).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. Even if you use v0 or v4 or specify full_action_space=False during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -40,9 +47,10 @@ instead. The respective observation spaces are
The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Venture-v5")
```
@@ -60,6 +68,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Venture-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/video_pinball.md
View File

@@ -1,6 +1,7 @@
---
title: Video Pinball
---
# Video Pinball
```{figure} ../../_static/videos/atari/video_pinball.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/VideoPinball-v5")` |
## Description
Your goal is to keep the ball in play as long as possible and to score as many points as possible. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=588).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -35,13 +38,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 6 | UPFIRE |
| 7 | RIGHTFIRE |
| 8 | LEFTFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -52,9 +59,10 @@ instead. The respective observation spaces are
The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/'VideoPinball-v5")
```
@@ -72,6 +80,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("VideoPinball-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/wizard_of_wor.md
View File

@@ -1,6 +1,7 @@
---
title: Wizard of Wor
---
# Wizard of Wor
```{figure} ../../_static/videos/atari/wizard_of_wor.gif
@@ -19,9 +20,11 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/WizardOfWor-v5")` |
## Description
Your goal is to beat the Wizard using your laser and radar scanner. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=598).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. However, if you use v0 or v4 or specify full_action_space=False during initialization, only a reduced number of actions (those that are meaningful in this game) are available. The reduced action space may depend on the flavor of the environment (the combination of mode and difficulty). The reduced action space for the default flavor looks like this:
| Num | Action |
@@ -36,13 +39,17 @@ By default, all actions that can be performed on an Atari 2600 are available in
| 7 | RIGHTFIRE |
| 8 | LEFTFIRE |
| 9 | DOWNFIRE |
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -53,9 +60,10 @@ instead. The respective observation spaces are
The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/WizardOfWor-v5")
```
@@ -73,6 +81,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("WizardOfWor-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

11
docs/environments/atari/zaxxon.md
View File

@@ -2,6 +2,7 @@
title: Zaxxon
lastpage:
---
# Zaxxon
```{figure} ../../_static/videos/atari/zaxxon.gif
@@ -20,17 +21,23 @@ This environment is part of the <a href='..'>Atari environments</a>. Please read
| Import | `gymnasium.make("ALE/Zaxxon-v5")` |
## Description
Your goal is to stop the evil robot Zaxxon and its armies from enslaving the galaxy by piloting your fighter and shooting enemies. Detailed documentation can be found on [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=606).
## Actions
By default, all actions that can be performed on an Atari 2600 are available in this environment. Even if you use v0 or v4 or specify full_action_space=False during initialization, all actions will be available in the default flavor.
## Observations
By default, the environment returns the RGB image that is displayed to human players as an observation. However, it is
possible to observe
- The 128 Bytes of RAM of the console
- A grayscale image
instead. The respective observation spaces are
- `Box([0 ... 0], [255 ... 255], (128,), uint8)`
- `Box([[0 ... 0]
...
@@ -41,9 +48,10 @@ instead. The respective observation spaces are
The general article on Atari environments outlines different ways to instantiate corresponding environments
via `gymnasium.make`.
## Arguments
```
```python
env = gymnasium.make("ALE/Zaxxon-v5")
```
@@ -59,6 +67,7 @@ the general article on Atari environments.
The versions v0 and v4 are not contained in the "ALE" namespace. I.e. they are instantiated via `gymnasium.make("Zaxxon-v0")`
## Version History
A thorough discussion of the intricate differences between the versions and configurations can be found in the
general article on Atari environments.

43
docs/environments/third_party_environments.md
View File

@@ -9,134 +9,175 @@ There are a number of Reinforcement Learning environments built by authors not i
## Video Game environments
### [stable-retro: Classic retro games, a maintained version of OpenAI Retro](https://github.com/MatPoliquin/stable-retro)
Supported fork of gym-retro with additional games, states, scenarios, etc. Open to PRs of additional games, features, and platforms since gym-retro is no longer maintained
### [flappy-bird-gym: A Flappy Bird environment for Gym](https://github.com/Talendar/flappy-bird-gym)
A simple environment for single-agent reinforcement learning algorithms on a clone of [Flappy Bird](https://en.wikipedia.org/wiki/Flappy_Bird), the hugely popular arcade-style mobile game. Both state and pixel observation environments are available.
### [gym-derk: GPU accelerated MOBA environment](https://gym.derkgame.com/)
This is a 3v3 MOBA environment where you train creatures to fight each other. It runs entirely on the GPU so you can easily have hundreds of instances running in parallel. There are around 15 items for the creatures, 60 "senses", 5 actions, and roughly 23 tweakable rewards. It's also possible to benchmark an agent against other agents online. It's available for free for training for personal use, and otherwise costs money; see licensing details on the website
### [SlimeVolleyGym: A simple environment for single and multi-agent reinforcement learning](https://github.com/hardmaru/slimevolleygym)
A simple environment for benchmarking single and multi-agent reinforcement learning algorithms on a clone of Slime Volleyball game. The only dependencies are gym and NumPy. Both state and pixel observation environments are available. The motivation of this environment is to easily enable trained agents to play against each other, and also facilitate the training of agents directly in a multi-agent setting, thus adding an extra dimension for evaluating an agent's performance.
### [Unity ML Agents: Environments for Unity game engine](https://github.com/Unity-Technologies/ml-agents)
Gym wrappers for arbitrary and premade environments with the Unity game engine.
### [PGE: Parallel Game Engine](https://github.com/222464/PGE)
PGE is a FOSS 3D engine for AI simulations and can interoperate with the Gym. Contains environments with modern 3D graphics, and uses Bullet for physics.
## Robotics environments
### [gym-jiminy: Training Robots in Jiminy](https://github.com/duburcqa/jiminy)
gym-jiminy presents an extension of the initial Gym for robotics using Jiminy, an extremely fast and light-weight simulator for poly-articulated systems using Pinocchio for physics evaluation and Meshcat for web-based 3D rendering.
### [gym-pybullet-drones: Environments for quadcopter control](https://github.com/JacopoPan/gym-pybullet-drones)
A simple environment using [PyBullet](https://github.com/bulletphysics/bullet3) to simulate the dynamics of a [Bitcraze Crazyflie 2.x](https://www.bitcraze.io/documentation/hardware/crazyflie_2_1/crazyflie_2_1-datasheet.pdf) nanoquadrotor.
### [MarsExplorer: Environments for controlling robot on Mars](https://github.com/dimikout3/MarsExplorer)
Mars Explorer is a Gym compatible environment designed and developed as an initial endeavor to bridge the gap between powerful Deep Reinforcement Learning methodologies and the problem of exploration/coverage of an unknown terrain.
### [panda-gym: Robotics environments using the PyBullet physics engine](https://github.com/qgallouedec/panda-gym/)
PyBullet based simulations of a robotic arm moving objects.
### [robo-gym: Real-world and simulation robotics](https://github.com/jr-robotics/robo-gym)
Robo-gym provides a collection of reinforcement learning environments involving robotic tasks applicable in both simulation and real-world robotics.
### [Offworld-gym](https://github.com/offworld-projects/offworld-gym)
Gym environments that let you control physics robotics in a laboratory via the internet.
### [safe-control-gym](https://github.com/utiasDSL/safe-control-gym)
PyBullet based CartPole and Quadrotor environments—with [CasADi](https://web.casadi.org) (symbolic) *a priori* dynamics and constraints—for learning-based control and model-based reinforcement learning.
### [gym-softrobot: Soft-robotics environments](https://github.com/skim0119/gym-softrobot/)
A large-scale benchmark for co-optimizing the design and control of soft robots.
### [iGibson](https://github.com/StanfordVL/iGibson/)
A Simulation Environment to train Robots in Large Realistic Interactive Scenes
### [DexterousHands: dual dexterous hand manipulation tasks](https://github.com/PKU-MARL/DexterousHands/)
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
### [OmniIsaacGymEnvs](https://github.com/NVIDIA-Omniverse/OmniIsaacGymEnvs/)
Reinforcement Learning Environments for Omniverse Isaac Gym
## Autonomous Driving environments
### [sumo-rl](https://github.com/LucasAlegre/sumo-rl)
Gym wrapper for various environments in the Sumo traffic simulator
### [gym-duckietown](https://github.com/duckietown/gym-duckietown)
A lane-following simulator built for the [Duckietown](http://duckietown.org/) project (small-scale self-driving car course).
### [gym-electric-motor](https://github.com/upb-lea/gym-electric-motor)
An environment for simulating a wide variety of electric drives taking into account different types of electric motors and converters. Control schemes can be continuous, yielding a voltage duty cycle, or discrete, determining converter switching states directly.
### [highway-env](https://github.com/eleurent/highway-env)
An environment for behavioral planning in autonomous driving, with an emphasis on high-level perception and decision rather than low-level sensing and control. The difficulty of the task lies in understanding the social interactions with other drivers, whose behaviors are uncertain. Several scenes are proposed, such as highway, merge, intersection and roundabout.
### [CommonRoad-RL](https://commonroad.in.tum.de/tools/commonroad-rl)
A Gym for solving motion planning problems for various traffic scenarios compatible with [CommonRoad benchmarks](https://commonroad.in.tum.de/scenarios), which provides configurable rewards, action spaces, and observation spaces.
### [tmrl: TrackMania 2020 through RL](https://github.com/trackmania-rl/tmrl/)
tmrl is a distributed framework for training Deep Reinforcement Learning AIs in real-time applications. It is demonstrated on the TrackMania 2020 video game.
### [racing_dreamer](https://github.com/CPS-TUWien/racing_dreamer/)
Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing
### [l2r: Multimodal control environment where agents learn how to race](https://github.com/learn-to-race/l2r/)
An open-source reinforcement learning environment for autonomous racing.
### [racecar_gym](https://github.com/axelbr/racecar_gym/)
A gym environment for a miniature racecar using the pybullet physics engine.
## Other environments
### [CompilerGym: Optimise compiler tasks](https://github.com/facebookresearch/CompilerGym)
Reinforcement learning environments for compiler optimization tasks, such as LLVM phase ordering, GCC flag tuning, and CUDA loop nest code generation.
### [CARL: context adaptive RL](https://github.com/automl/CARL)
Configurable reinforcement learning environments for testing generalization, e.g. CartPole with variable pole lengths or Brax robots with different ground frictions.
### [matrix-mdp: Easily create discrete MDPs](https://github.com/Paul-543NA/matrix-mdp-gym)
An environment to easily implement discrete MDPs as gym environments. Turn a set of matrices (`P_0(s)`, `P(s'| s, a)` and `R(s', s, a)`) into a gym environment that represents the discrete MDP ruled by these dynamics.
### [mo-gym: Multi-objective Reinforcement Learning environments](https://github.com/LucasAlegre/mo-gym)
Multi-objective RL (MORL) gym environments, where the reward is a NumPy array of different (possibly conflicting) objectives.
### [gym-cellular-automata: Cellular Automata environments](https://github.com/elbecerrasoto/gym-cellular-automata)
Environments where the agent interacts with _Cellular Automata_ by changing its cell states.
### [gym-sokoban: 2D Transportation Puzzles](https://github.com/mpSchrader/gym-sokoban)
The environment consists of transportation puzzles in which the player's goal is to push all boxes to the warehouse's storage locations. The advantage of the environment is that it generates a new random level every time it is initialized or reset, which prevents overfitting to predefined levels.
### [DACBench: Benchmark Library for Dynamic Algorithm configuration](https://github.com/automl/DACBench)
Environments for hyperparameter configuration using RL. Includes cheap surrogate benchmarks as well as real-world algorithms from e.g. AI Planning, Evolutionary Computation and Deep Learning.
### [NLPGym: A toolkit to develop RL agents to solve NLP tasks](https://github.com/rajcscw/nlp-gym)
[NLPGym](https://arxiv.org/pdf/2011.08272v1.pdf) provides interactive environments for standard NLP tasks such as sequence tagging, question answering, and sequence classification. Users can easily customize the tasks with their datasets, observations, features and reward functions.
### [gym-saturation: Environments used to prove theorems](https://github.com/inpefess/gym-saturation)
An environment for guiding automated theorem provers based on saturation algorithms (e.g. [Vampire](https://github.com/vprover/vampire)).
### [ShinRL: Environments for evaluating RL algorithms](https://github.com/omron-sinicx/ShinRL/)
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives (Deep RL Workshop 2021)
### [gymnax: Hardware Accelerated RL Environments](https://github.com/RobertTLange/gymnax/)
RL Environments in JAX which allows for highly vectorised environments with support for a number of environments, Gym, MinAtari, bsuite and more.
### [gym-anytrading: Financial trading environments for FOREX and STOCKS](https://github.com/AminHP/gym-anytrading)
AnyTrading is a collection of Gym environments for reinforcement learning-based trading algorithms with a great focus on simplicity, flexibility, and comprehensiveness.
### [gym-mtsim: Financial trading for MetaTrader 5 platform](https://github.com/AminHP/gym-mtsim)
MtSim is a simulator for the MetaTrader 5 trading platform for reinforcement learning-based trading algorithms. MetaTrader 5 is a multi-asset platform that allows trading Forex, Stocks, Crypto, and Futures.
### [openmodelica-microgrid-gym: Environments for controlling power electronic converters in microgrids](https://github.com/upb-lea/openmodelica-microgrid-gym)
The OpenModelica Microgrid Gym (OMG) package is a software toolbox for the simulation and control optimization of microgrids based on energy conversion by power electronic converters.
### [mobile-env: Environments for coordination of wireless mobile networks](https://github.com/stefanbschneider/mobile-env/)
An open, minimalist Gym environment for autonomous coordination in wireless mobile networks.
### [GymFC: A flight control tuning and training framework](https://github.com/wil3/gymfc/)
GymFC is a modular framework for synthesizing neuro-flight controllers. The architecture integrates digital twinning concepts to provide a seamless transfer of trained policies to hardware. The environment has been used to generate policies for the world's first open-source neural network flight control firmware [Neuroflight](https://github.com/wil3/neuroflight).
GymFC is a modular framework for synthesizing neuro-flight controllers. The architecture integrates digital twinning concepts to provide a seamless transfer of trained policies to hardware. The environment has been used to generate policies for the world's first open-source neural network flight control firmware [Neuroflight](https://github.com/wil3/neuroflight).

1
docs/index.md
View File

@@ -6,7 +6,6 @@ lastpage:
# Gymnasium is a standard API for reinforcement learning, and a diverse collection of reference environments
```{figure} _static/videos/box2d/lunar_lander_continuous.gif
:alt: Lunar Lander
:width: 500

1
docs/scripts/gen_envs_display.py
View File

@@ -1,6 +1,7 @@
import os
import sys
all_envs = [
{
"id": "mujoco",

3
docs/scripts/gen_gifs.py
View File

@@ -6,9 +6,10 @@ import re
from PIL import Image
from tqdm import tqdm
from utils import kill_strs
import gymnasium
from utils import kill_strs
# snake to camel case: https://stackoverflow.com/questions/1175208/elegant-python-function-to-convert-camelcase-to-snake-case # noqa: E501
pattern = re.compile(r"(?<!^)(?=[A-Z])")

3
docs/scripts/gen_mds.py
View File

@@ -7,9 +7,10 @@ from functools import reduce
import numpy as np
from tqdm import tqdm
from utils import kill_strs, trim
import gymnasium as gym
from utils import kill_strs, trim
LAYOUT = "env"

1
docs/scripts/move_404.py
View File

@@ -1,5 +1,6 @@
import sys
if __name__ == "__main__":
if len(sys.argv) < 2:
print("Provide a path")

1
docs/tutorials/blackjack_tutorial.py
View File

@@ -51,6 +51,7 @@ from tqdm import tqdm
import gymnasium as gym
# Let's start by creating the blackjack environment.
# Note: We are going to follow the rules from Sutton & Barto.
# Other versions of the game can be found below for you to experiment.

1
docs/tutorials/reinforce_invpend_gym_v26.py
View File

@@ -53,6 +53,7 @@ from torch.distributions.normal import Normal
import gymnasium as gym
plt.rcParams["figure.figsize"] = (10, 5)

1
gymnasium/core.py
View File

@@ -8,6 +8,7 @@ import numpy as np
from gymnasium import spaces
from gymnasium.utils import seeding
if TYPE_CHECKING:
from gymnasium.envs.registration import EnvSpec

1
gymnasium/envs/__init__.py
View File

@@ -8,6 +8,7 @@ from gymnasium.envs.registration import (
spec,
)
# Classic
# ----------------------------------------

1
gymnasium/envs/box2d/bipedal_walker.py
View File

@@ -10,6 +10,7 @@ from gymnasium import error, spaces
from gymnasium.error import DependencyNotInstalled
from gymnasium.utils import EzPickle
try:
import Box2D
from Box2D.b2 import (

1
gymnasium/envs/box2d/car_dynamics.py
View File

@@ -14,6 +14,7 @@ import numpy as np
from gymnasium.error import DependencyNotInstalled
try:
from Box2D.b2 import fixtureDef, polygonShape, revoluteJointDef
except ImportError:

1
gymnasium/envs/box2d/car_racing.py
View File

@@ -11,6 +11,7 @@ from gymnasium.envs.box2d.car_dynamics import Car
from gymnasium.error import DependencyNotInstalled, InvalidAction
from gymnasium.utils import EzPickle
try:
import Box2D
from Box2D.b2 import contactListener, fixtureDef, polygonShape

1
gymnasium/envs/box2d/lunar_lander.py
View File

@@ -12,6 +12,7 @@ from gymnasium.error import DependencyNotInstalled
from gymnasium.utils import EzPickle, colorize
from gymnasium.utils.step_api_compatibility import step_api_compatibility
try:
import Box2D
from Box2D.b2 import (

1
gymnasium/envs/classic_control/acrobot.py
View File

@@ -9,6 +9,7 @@ from gymnasium import Env, spaces
from gymnasium.envs.classic_control import utils
from gymnasium.error import DependencyNotInstalled
__copyright__ = "Copyright 2013, RLPy http://acl.mit.edu/RLPy"
__credits__ = [
"Alborz Geramifard",

1
gymnasium/envs/classic_control/pendulum.py
View File

@@ -10,6 +10,7 @@ from gymnasium import spaces
from gymnasium.envs.classic_control import utils
from gymnasium.error import DependencyNotInstalled
DEFAULT_X = np.pi
DEFAULT_Y = 1.0

1
gymnasium/envs/mujoco/ant_v3.py
View File

@@ -4,6 +4,7 @@ from gymnasium import utils
from gymnasium.envs.mujoco import MuJocoPyEnv
from gymnasium.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"distance": 4.0,
}

1
gymnasium/envs/mujoco/ant_v4.py
View File

@@ -4,6 +4,7 @@ from gymnasium import utils
from gymnasium.envs.mujoco import MujocoEnv
from gymnasium.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"distance": 4.0,
}

0
gymnasium/envs/mujoco/assets/humanoid.xml Executable file → Normal file
View File

0
gymnasium/envs/mujoco/assets/humanoidstandup.xml Executable file → Normal file
View File

1
gymnasium/envs/mujoco/half_cheetah_v3.py
View File

@@ -6,6 +6,7 @@ from gymnasium import utils
from gymnasium.envs.mujoco import MuJocoPyEnv
from gymnasium.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"distance": 4.0,
}

1
gymnasium/envs/mujoco/half_cheetah_v4.py
View File

@@ -6,6 +6,7 @@ from gymnasium import utils
from gymnasium.envs.mujoco import MujocoEnv
from gymnasium.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"distance": 4.0,
}

1
gymnasium/envs/mujoco/hopper_v3.py
View File

@@ -6,6 +6,7 @@ from gymnasium import utils
from gymnasium.envs.mujoco import MuJocoPyEnv
from gymnasium.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"trackbodyid": 2,
"distance": 3.0,

1
gymnasium/envs/mujoco/hopper_v4.py
View File

@@ -4,6 +4,7 @@ from gymnasium import utils
from gymnasium.envs.mujoco import MujocoEnv
from gymnasium.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"trackbodyid": 2,
"distance": 3.0,

Some files were not shown because too many files have changed in this diff Show More