Files
Gymnasium/gymnasium/envs/box2d/lunar_lander.py

820 lines
29 KiB
Python
Raw Normal View History

__credits__ = ["Andrea PIERRÉ"]
2021-07-29 02:26:34 +02:00
import math
import warnings
from typing import TYPE_CHECKING, Optional
Seeding update (#2422) * Ditch most of the seeding.py and replace np_random with the numpy default_rng. Let's see if tests pass * Updated a bunch of RNG calls from the RandomState API to Generator API * black; didn't expect that, did ya? * Undo a typo * blaaack * More typo fixes * Fixed setting/getting state in multidiscrete spaces * Fix typo, fix a test to work with the new sampling * Correctly (?) pass the randomly generated seed if np_random is called with None as seed * Convert the Discrete sample to a python int (as opposed to np.int64) * Remove some redundant imports * First version of the compatibility layer for old-style RNG. Mainly to trigger tests. * Removed redundant f-strings * Style fixes, removing unused imports * Try to make tests pass by removing atari from the dockerfile * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * First attempt at deprecating `env.seed` and supporting `env.reset(seed=seed)` instead. Tests should hopefully pass but throw up a million warnings. * black; didn't expect that, didya? * Rename the reset parameter in VecEnvs back to `seed` * Updated tests to use the new seeding method * Removed a bunch of old `seed` calls. Fixed a bug in AsyncVectorEnv * Stop Discrete envs from doing part of the setup (and using the randomness) in init (as opposed to reset) * Add explicit seed to wrappers reset * Remove an accidental return * Re-add some legacy functions with a warning. * Use deprecation instead of regular warnings for the newly deprecated methods/functions
2021-12-08 22:14:15 +01:00
2016-05-03 22:27:42 +03:00
import numpy as np
import gymnasium as gym
2022-09-08 10:10:07 +01:00
from gymnasium import error, spaces
from gymnasium.error import DependencyNotInstalled
from gymnasium.utils import EzPickle, colorize
from gymnasium.utils.step_api_compatibility import step_api_compatibility
2016-05-03 22:27:42 +03:00
try:
import Box2D
from Box2D.b2 import (
circleShape,
contactListener,
edgeShape,
fixtureDef,
polygonShape,
revoluteJointDef,
)
except ImportError:
2022-09-08 10:11:31 +01:00
raise DependencyNotInstalled(
"box2d is not installed, run `pip install gymnasium[box2d]`"
)
if TYPE_CHECKING:
import pygame
FPS = 50
2021-07-29 02:26:34 +02:00
SCALE = 30.0 # affects how fast-paced the game is, forces should be adjusted as well
MAIN_ENGINE_POWER = 13.0
SIDE_ENGINE_POWER = 0.6
2016-05-03 22:27:42 +03:00
2021-07-29 02:26:34 +02:00
INITIAL_RANDOM = 1000.0 # Set 1500 to make game harder
2016-05-03 22:27:42 +03:00
2021-07-29 02:26:34 +02:00
LANDER_POLY = [(-14, +17), (-17, 0), (-17, -10), (+17, -10), (+17, 0), (+14, +17)]
2016-05-03 22:27:42 +03:00
LEG_AWAY = 20
LEG_DOWN = 18
LEG_W, LEG_H = 2, 8
LEG_SPRING_TORQUE = 40
SIDE_ENGINE_HEIGHT = 14.0
SIDE_ENGINE_AWAY = 12.0
2016-05-03 22:27:42 +03:00
VIEWPORT_W = 600
VIEWPORT_H = 400
2016-05-03 22:27:42 +03:00
class ContactDetector(contactListener):
def __init__(self, env):
2016-05-25 11:16:15 +03:00
contactListener.__init__(self)
self.env = env
2016-05-03 22:27:42 +03:00
def BeginContact(self, contact):
2021-07-29 15:39:42 -04:00
if (
self.env.lander == contact.fixtureA.body
or self.env.lander == contact.fixtureB.body
):
2016-05-03 22:27:42 +03:00
self.env.game_over = True
for i in range(2):
if self.env.legs[i] in [contact.fixtureA.body, contact.fixtureB.body]:
self.env.legs[i].ground_contact = True
def EndContact(self, contact):
for i in range(2):
if self.env.legs[i] in [contact.fixtureA.body, contact.fixtureB.body]:
self.env.legs[i].ground_contact = False
2016-05-03 22:27:42 +03:00
class LunarLander(gym.Env, EzPickle):
"""
## Description
This environment is a classic rocket trajectory optimization problem.
According to Pontryagin's maximum principle, it is optimal to fire the
engine at full throttle or turn it off. This is the reason why this
environment has discrete actions: engine on or off.
There are two environment versions: discrete or continuous.
The landing pad is always at coordinates (0,0). The coordinates are the
first two numbers in the state vector.
Landing outside of the landing pad is possible. Fuel is infinite, so an agent
can learn to fly and then land on its first attempt.
To see a heuristic landing, run:
```
2022-09-08 10:10:07 +01:00
python gymnasium/envs/box2d/lunar_lander.py
```
<!-- To play yourself, run: -->
<!-- python examples/agents/keyboard_agent.py LunarLander-v2 -->
## Action Space
There are four discrete actions available: do nothing, fire left
orientation engine, fire main engine, fire right orientation engine.
## Observation Space
The state is an 8-dimensional vector: the coordinates of the lander in `x` & `y`, its linear
velocities in `x` & `y`, its angle, its angular velocity, and two booleans
that represent whether each leg is in contact with the ground or not.
## Rewards
After every step a reward is granted. The total reward of an episode is the
sum of the rewards for all the steps within that episode.
For each step, the reward:
- is increased/decreased the closer/further the lander is to the landing pad.
- is increased/decreased the slower/faster the lander is moving.
- is decreased the more the lander is tilted (angle not horizontal).
- is increased by 10 points for each leg that is in contact with the ground.
- is decreased by 0.03 points each frame a side engine is firing.
- is decreased by 0.3 points each frame the main engine is firing.
The episode receive an additional reward of -100 or +100 points for crashing or landing safely respectively.
An episode is considered a solution if it scores at least 200 points.
## Starting State
The lander starts at the top center of the viewport with a random initial
force applied to its center of mass.
## Episode Termination
The episode finishes if:
1) the lander crashes (the lander body gets in contact with the moon);
2) the lander gets outside of the viewport (`x` coordinate is greater than 1);
3) the lander is not awake. From the [Box2D docs](https://box2d.org/documentation/md__d_1__git_hub_box2d_docs_dynamics.html#autotoc_md61),
a body which is not awake is a body which doesn't move and doesn't
collide with any other body:
> When Box2D determines that a body (or group of bodies) has come to rest,
> the body enters a sleep state which has very little CPU overhead. If a
> body is awake and collides with a sleeping body, then the sleeping body
> wakes up. Bodies will also wake up if a joint or contact attached to
> them is destroyed.
## Arguments
To use to the _continuous_ environment, you need to specify the
`continuous=True` argument like below:
```python
import gymnasium as gym
env = gym.make(
"LunarLander-v2",
continuous: bool = False,
gravity: float = -10.0,
enable_wind: bool = False,
wind_power: float = 15.0,
turbulence_power: float = 1.5,
)
```
If `continuous=True` is passed, continuous actions (corresponding to the throttle of the engines) will be used and the
action space will be `Box(-1, +1, (2,), dtype=np.float32)`.
The first coordinate of an action determines the throttle of the main engine, while the second
coordinate specifies the throttle of the lateral boosters.
Given an action `np.array([main, lateral])`, the main engine will be turned off completely if
`main < 0` and the throttle scales affinely from 50% to 100% for `0 <= main <= 1` (in particular, the
main engine doesn't work with less than 50% power).
Similarly, if `-0.5 < lateral < 0.5`, the lateral boosters will not fire at all. If `lateral < -0.5`, the left
booster will fire, and if `lateral > 0.5`, the right booster will fire. Again, the throttle scales affinely
from 50% to 100% between -1 and -0.5 (and 0.5 and 1, respectively).
`gravity` dictates the gravitational constant, this is bounded to be within 0 and -12.
If `enable_wind=True` is passed, there will be wind effects applied to the lander.
The wind is generated using the function `tanh(sin(2 k (t+C)) + sin(pi k (t+C)))`.
`k` is set to 0.01.
`C` is sampled randomly between -9999 and 9999.
`wind_power` dictates the maximum magnitude of linear wind applied to the craft. The recommended value for `wind_power` is between 0.0 and 20.0.
`turbulence_power` dictates the maximum magnitude of rotational wind applied to the craft. The recommended value for `turbulence_power` is between 0.0 and 2.0.
## Version History
- v2: Count energy spent and in v0.24, added turbulence with wind power and turbulence_power parameters
- v1: Legs contact with ground added in state vector; contact with ground
give +10 reward points, and -10 if then lose contact; reward
renormalized to 200; harder initial random push.
- v0: Initial version
<!-- ## References -->
## Credits
Created by Oleg Klimov
"""
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
metadata = {
"render_modes": ["human", "rgb_array"],
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
"render_fps": FPS,
}
2016-05-03 22:27:42 +03:00
def __init__(
self,
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
render_mode: Optional[str] = None,
continuous: bool = False,
gravity: float = -10.0,
enable_wind: bool = False,
wind_power: float = 15.0,
turbulence_power: float = 1.5,
):
EzPickle.__init__(
self,
render_mode,
continuous,
gravity,
enable_wind,
wind_power,
turbulence_power,
)
assert (
-12.0 < gravity and gravity < 0.0
), f"gravity (current value: {gravity}) must be between -12 and 0"
self.gravity = gravity
if 0.0 > wind_power or wind_power > 20.0:
warnings.warn(
colorize(
f"WARN: wind_power value is recommended to be between 0.0 and 20.0, (current value: {wind_power})",
"yellow",
),
)
self.wind_power = wind_power
if 0.0 > turbulence_power or turbulence_power > 2.0:
warnings.warn(
colorize(
f"WARN: turbulence_power value is recommended to be between 0.0 and 2.0, (current value: {turbulence_power})",
"yellow",
),
)
self.turbulence_power = turbulence_power
self.enable_wind = enable_wind
self.wind_idx = np.random.randint(-9999, 9999)
self.torque_idx = np.random.randint(-9999, 9999)
self.screen: pygame.Surface = None
self.clock = None
self.isopen = True
self.world = Box2D.b2World(gravity=(0, gravity))
2016-05-03 22:27:42 +03:00
self.moon = None
self.lander: Optional[Box2D.b2Body] = None
2016-05-03 22:27:42 +03:00
self.particles = []
self.prev_reward = None
self.continuous = continuous
low = np.array(
[
# these are bounds for position
# realistically the environment should have ended
# long before we reach more than 50% outside
-1.5,
-1.5,
# velocity bounds is 5x rated speed
-5.0,
-5.0,
-math.pi,
-5.0,
-0.0,
-0.0,
]
).astype(np.float32)
high = np.array(
[
# these are bounds for position
# realistically the environment should have ended
# long before we reach more than 50% outside
1.5,
1.5,
# velocity bounds is 5x rated speed
5.0,
5.0,
math.pi,
5.0,
1.0,
1.0,
]
).astype(np.float32)
# useful range is -1 .. +1, but spikes can be higher
self.observation_space = spaces.Box(low, high)
if self.continuous:
# Action is two floats [main engine, left-right engines].
# Main engine: -1..0 off, 0..+1 throttle from 50% to 100% power. Engine can't work with less than 50% power.
# Left-right: -1.0..-0.5 fire left engine, +0.5..+1.0 fire right engine, -0.5..0.5 off
self.action_space = spaces.Box(-1, +1, (2,), dtype=np.float32)
else:
# Nop, fire left engine, main engine, right engine
self.action_space = spaces.Discrete(4)
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
self.render_mode = render_mode
2016-05-03 22:27:42 +03:00
def _destroy(self):
2021-07-29 02:26:34 +02:00
if not self.moon:
return
2016-05-25 11:16:15 +03:00
self.world.contactListener = None
2016-05-03 22:27:42 +03:00
self._clean_particles(True)
self.world.DestroyBody(self.moon)
self.moon = None
self.world.DestroyBody(self.lander)
self.lander = None
self.world.DestroyBody(self.legs[0])
self.world.DestroyBody(self.legs[1])
def reset(
self,
*,
seed: Optional[int] = None,
options: Optional[dict] = None,
):
Seeding update (#2422) * Ditch most of the seeding.py and replace np_random with the numpy default_rng. Let's see if tests pass * Updated a bunch of RNG calls from the RandomState API to Generator API * black; didn't expect that, did ya? * Undo a typo * blaaack * More typo fixes * Fixed setting/getting state in multidiscrete spaces * Fix typo, fix a test to work with the new sampling * Correctly (?) pass the randomly generated seed if np_random is called with None as seed * Convert the Discrete sample to a python int (as opposed to np.int64) * Remove some redundant imports * First version of the compatibility layer for old-style RNG. Mainly to trigger tests. * Removed redundant f-strings * Style fixes, removing unused imports * Try to make tests pass by removing atari from the dockerfile * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * First attempt at deprecating `env.seed` and supporting `env.reset(seed=seed)` instead. Tests should hopefully pass but throw up a million warnings. * black; didn't expect that, didya? * Rename the reset parameter in VecEnvs back to `seed` * Updated tests to use the new seeding method * Removed a bunch of old `seed` calls. Fixed a bug in AsyncVectorEnv * Stop Discrete envs from doing part of the setup (and using the randomness) in init (as opposed to reset) * Add explicit seed to wrappers reset * Remove an accidental return * Re-add some legacy functions with a warning. * Use deprecation instead of regular warnings for the newly deprecated methods/functions
2021-12-08 22:14:15 +01:00
super().reset(seed=seed)
2016-05-03 22:27:42 +03:00
self._destroy()
self.world.contactListener_keepref = ContactDetector(self)
self.world.contactListener = self.world.contactListener_keepref
2016-05-03 22:27:42 +03:00
self.game_over = False
self.prev_shaping = None
2021-07-29 02:26:34 +02:00
W = VIEWPORT_W / SCALE
H = VIEWPORT_H / SCALE
2016-05-03 22:27:42 +03:00
# terrain
CHUNKS = 11
2021-07-29 02:26:34 +02:00
height = self.np_random.uniform(0, H / 2, size=(CHUNKS + 1,))
chunk_x = [W / (CHUNKS - 1) * i for i in range(CHUNKS)]
self.helipad_x1 = chunk_x[CHUNKS // 2 - 1]
self.helipad_x2 = chunk_x[CHUNKS // 2 + 1]
self.helipad_y = H / 4
height[CHUNKS // 2 - 2] = self.helipad_y
height[CHUNKS // 2 - 1] = self.helipad_y
height[CHUNKS // 2 + 0] = self.helipad_y
height[CHUNKS // 2 + 1] = self.helipad_y
height[CHUNKS // 2 + 2] = self.helipad_y
2021-07-29 15:39:42 -04:00
smooth_y = [
0.33 * (height[i - 1] + height[i + 0] + height[i + 1])
for i in range(CHUNKS)
]
2021-07-29 02:26:34 +02:00
2021-07-29 15:39:42 -04:00
self.moon = self.world.CreateStaticBody(
shapes=edgeShape(vertices=[(0, 0), (W, 0)])
)
2016-05-03 22:27:42 +03:00
self.sky_polys = []
2021-07-29 02:26:34 +02:00
for i in range(CHUNKS - 1):
p1 = (chunk_x[i], smooth_y[i])
2021-07-29 02:26:34 +02:00
p2 = (chunk_x[i + 1], smooth_y[i + 1])
self.moon.CreateEdgeFixture(vertices=[p1, p2], density=0, friction=0.1)
self.sky_polys.append([p1, p2, (p2[0], H), (p1[0], H)])
2016-05-03 22:27:42 +03:00
self.moon.color1 = (0.0, 0.0, 0.0)
self.moon.color2 = (0.0, 0.0, 0.0)
2016-05-03 22:27:42 +03:00
2021-07-29 02:26:34 +02:00
initial_y = VIEWPORT_H / SCALE
self.lander: Box2D.b2Body = self.world.CreateDynamicBody(
2021-07-29 02:26:34 +02:00
position=(VIEWPORT_W / SCALE / 2, initial_y),
2016-05-03 22:27:42 +03:00
angle=0.0,
2021-07-29 02:26:34 +02:00
fixtures=fixtureDef(
2021-07-29 15:39:42 -04:00
shape=polygonShape(
vertices=[(x / SCALE, y / SCALE) for x, y in LANDER_POLY]
),
2016-05-03 22:27:42 +03:00
density=5.0,
friction=0.1,
categoryBits=0x0010,
2021-07-29 02:26:34 +02:00
maskBits=0x001, # collide only with ground
restitution=0.0,
), # 0.99 bouncy
)
self.lander.color1 = (128, 102, 230)
self.lander.color2 = (77, 77, 128)
2021-07-29 02:26:34 +02:00
self.lander.ApplyForceToCenter(
(
self.np_random.uniform(-INITIAL_RANDOM, INITIAL_RANDOM),
self.np_random.uniform(-INITIAL_RANDOM, INITIAL_RANDOM),
),
True,
)
2016-05-03 22:27:42 +03:00
self.legs = []
for i in [-1, +1]:
2016-05-03 22:27:42 +03:00
leg = self.world.CreateDynamicBody(
2021-07-29 02:26:34 +02:00
position=(VIEWPORT_W / SCALE / 2 - i * LEG_AWAY / SCALE, initial_y),
angle=(i * 0.05),
fixtures=fixtureDef(
2021-07-29 02:26:34 +02:00
shape=polygonShape(box=(LEG_W / SCALE, LEG_H / SCALE)),
2016-05-03 22:27:42 +03:00
density=1.0,
restitution=0.0,
categoryBits=0x0020,
2021-07-29 02:26:34 +02:00
maskBits=0x001,
),
)
leg.ground_contact = False
leg.color1 = (128, 102, 230)
leg.color2 = (77, 77, 128)
2016-05-03 22:27:42 +03:00
rjd = revoluteJointDef(
bodyA=self.lander,
bodyB=leg,
localAnchorA=(0, 0),
2021-07-29 02:26:34 +02:00
localAnchorB=(i * LEG_AWAY / SCALE, LEG_DOWN / SCALE),
2016-05-03 22:27:42 +03:00
enableMotor=True,
enableLimit=True,
maxMotorTorque=LEG_SPRING_TORQUE,
2021-07-29 02:26:34 +02:00
motorSpeed=+0.3 * i, # low enough not to jump back into the sky
)
if i == -1:
2021-07-29 15:39:42 -04:00
rjd.lowerAngle = (
+0.9 - 0.5
) # The most esoteric numbers here, angled legs have freedom to travel within
2016-05-03 22:27:42 +03:00
rjd.upperAngle = +0.9
else:
rjd.lowerAngle = -0.9
rjd.upperAngle = -0.9 + 0.5
leg.joint = self.world.CreateJoint(rjd)
self.legs.append(leg)
self.drawlist = [self.lander] + self.legs
if self.render_mode == "human":
self.render()
return self.step(np.array([0, 0]) if self.continuous else 0)[0], {}
2016-05-03 22:27:42 +03:00
def _create_particle(self, mass, x, y, ttl):
2016-05-03 22:27:42 +03:00
p = self.world.CreateDynamicBody(
2021-07-29 02:26:34 +02:00
position=(x, y),
2016-05-03 22:27:42 +03:00
angle=0.0,
2021-07-29 02:26:34 +02:00
fixtures=fixtureDef(
shape=circleShape(radius=2 / SCALE, pos=(0, 0)),
2016-05-03 22:27:42 +03:00
density=mass,
friction=0.1,
categoryBits=0x0100,
maskBits=0x001, # collide only with ground
2021-07-29 02:26:34 +02:00
restitution=0.3,
),
)
p.ttl = ttl
2016-05-03 22:27:42 +03:00
self.particles.append(p)
self._clean_particles(False)
return p
def _clean_particles(self, all):
while self.particles and (all or self.particles[0].ttl < 0):
2016-05-03 22:27:42 +03:00
self.world.DestroyBody(self.particles.pop(0))
def step(self, action):
assert self.lander is not None
# Update wind
assert self.lander is not None, "You forgot to call reset()"
if self.enable_wind and not (
self.legs[0].ground_contact or self.legs[1].ground_contact
):
# the function used for wind is tanh(sin(2 k x) + sin(pi k x)),
# which is proven to never be periodic, k = 0.01
wind_mag = (
math.tanh(
math.sin(0.02 * self.wind_idx)
+ (math.sin(math.pi * 0.01 * self.wind_idx))
)
* self.wind_power
)
self.wind_idx += 1
self.lander.ApplyForceToCenter(
(wind_mag, 0.0),
True,
)
# the function used for torque is tanh(sin(2 k x) + sin(pi k x)),
# which is proven to never be periodic, k = 0.01
torque_mag = math.tanh(
math.sin(0.02 * self.torque_idx)
+ (math.sin(math.pi * 0.01 * self.torque_idx))
) * (self.turbulence_power)
self.torque_idx += 1
self.lander.ApplyTorque(
(torque_mag),
True,
)
if self.continuous:
action = np.clip(action, -1, +1).astype(np.float32)
else:
assert self.action_space.contains(
action
), f"{action!r} ({type(action)}) invalid "
2016-05-03 22:27:42 +03:00
# Engines
2021-07-29 02:26:34 +02:00
tip = (math.sin(self.lander.angle), math.cos(self.lander.angle))
side = (-tip[1], tip[0])
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
dispersion = [self.np_random.uniform(-1.0, +1.0) / SCALE for _ in range(2)]
m_power = 0.0
2021-07-29 15:39:42 -04:00
if (self.continuous and action[0] > 0.0) or (
not self.continuous and action == 2
):
# Main engine
if self.continuous:
2021-07-29 02:26:34 +02:00
m_power = (np.clip(action[0], 0.0, 1.0) + 1.0) * 0.5 # 0.5..1.0
assert m_power >= 0.5 and m_power <= 1.0
else:
m_power = 1.0
# 4 is move a bit downwards, +-2 for randomness
ox = tip[0] * (4 / SCALE + 2 * dispersion[0]) + side[0] * dispersion[1]
2021-07-29 02:26:34 +02:00
oy = -tip[1] * (4 / SCALE + 2 * dispersion[0]) - side[1] * dispersion[1]
2016-05-03 22:27:42 +03:00
impulse_pos = (self.lander.position[0] + ox, self.lander.position[1] + oy)
2021-07-29 02:26:34 +02:00
p = self._create_particle(
3.5, # 3.5 is here to make particle speed adequate
impulse_pos[0],
impulse_pos[1],
m_power,
) # particles are just a decoration
p.ApplyLinearImpulse(
(ox * MAIN_ENGINE_POWER * m_power, oy * MAIN_ENGINE_POWER * m_power),
impulse_pos,
True,
)
self.lander.ApplyLinearImpulse(
(-ox * MAIN_ENGINE_POWER * m_power, -oy * MAIN_ENGINE_POWER * m_power),
impulse_pos,
True,
)
s_power = 0.0
2021-07-29 15:39:42 -04:00
if (self.continuous and np.abs(action[1]) > 0.5) or (
not self.continuous and action in [1, 3]
):
# Orientation engines
if self.continuous:
direction = np.sign(action[1])
s_power = np.clip(np.abs(action[1]), 0.5, 1.0)
assert s_power >= 0.5 and s_power <= 1.0
else:
2021-07-29 02:26:34 +02:00
direction = action - 2
s_power = 1.0
2021-07-29 15:39:42 -04:00
ox = tip[0] * dispersion[0] + side[0] * (
3 * dispersion[1] + direction * SIDE_ENGINE_AWAY / SCALE
)
oy = -tip[1] * dispersion[0] - side[1] * (
3 * dispersion[1] + direction * SIDE_ENGINE_AWAY / SCALE
)
2021-07-29 02:26:34 +02:00
impulse_pos = (
self.lander.position[0] + ox - tip[0] * 17 / SCALE,
self.lander.position[1] + oy + tip[1] * SIDE_ENGINE_HEIGHT / SCALE,
)
p = self._create_particle(0.7, impulse_pos[0], impulse_pos[1], s_power)
2021-07-29 02:26:34 +02:00
p.ApplyLinearImpulse(
(ox * SIDE_ENGINE_POWER * s_power, oy * SIDE_ENGINE_POWER * s_power),
impulse_pos,
True,
)
self.lander.ApplyLinearImpulse(
(-ox * SIDE_ENGINE_POWER * s_power, -oy * SIDE_ENGINE_POWER * s_power),
impulse_pos,
True,
)
self.world.Step(1.0 / FPS, 6 * 30, 2 * 30)
2016-05-03 22:27:42 +03:00
pos = self.lander.position
vel = self.lander.linearVelocity
state = [
2021-07-29 02:26:34 +02:00
(pos.x - VIEWPORT_W / SCALE / 2) / (VIEWPORT_W / SCALE / 2),
(pos.y - (self.helipad_y + LEG_DOWN / SCALE)) / (VIEWPORT_H / SCALE / 2),
vel.x * (VIEWPORT_W / SCALE / 2) / FPS,
vel.y * (VIEWPORT_H / SCALE / 2) / FPS,
self.lander.angle,
2021-07-29 02:26:34 +02:00
20.0 * self.lander.angularVelocity / FPS,
1.0 if self.legs[0].ground_contact else 0.0,
2021-07-29 02:26:34 +02:00
1.0 if self.legs[1].ground_contact else 0.0,
]
assert len(state) == 8
2016-05-03 22:27:42 +03:00
reward = 0
2021-07-29 02:26:34 +02:00
shaping = (
-100 * np.sqrt(state[0] * state[0] + state[1] * state[1])
- 100 * np.sqrt(state[2] * state[2] + state[3] * state[3])
- 100 * abs(state[4])
+ 10 * state[6]
+ 10 * state[7]
) # And ten points for legs contact, the idea is if you
# lose contact again after landing, you get negative reward
2016-05-03 22:27:42 +03:00
if self.prev_shaping is not None:
reward = shaping - self.prev_shaping
self.prev_shaping = shaping
2021-07-29 15:39:42 -04:00
reward -= (
m_power * 0.30
) # less fuel spent is better, about -30 for heuristic landing
2021-07-29 02:26:34 +02:00
reward -= s_power * 0.03
terminated = False
2016-05-03 22:27:42 +03:00
if self.game_over or abs(state[0]) >= 1.0:
terminated = True
reward = -100
2016-05-03 22:27:42 +03:00
if not self.lander.awake:
terminated = True
reward = +100
if self.render_mode == "human":
self.render()
return np.array(state, dtype=np.float32), reward, terminated, False, {}
2016-05-03 22:27:42 +03:00
def render(self):
if self.render_mode is None:
gym.logger.warn(
"You are calling render method without specifying any render mode. "
"You can specify the render_mode at initialization, "
f'e.g. gym("{self.spec.id}", render_mode="rgb_array")'
)
return
try:
import pygame
from pygame import gfxdraw
except ImportError:
raise DependencyNotInstalled(
2022-09-08 10:10:07 +01:00
"pygame is not installed, run `pip install gymnasium[box2d]`"
)
if self.screen is None and self.render_mode == "human":
pygame.init()
pygame.display.init()
self.screen = pygame.display.set_mode((VIEWPORT_W, VIEWPORT_H))
if self.clock is None:
self.clock = pygame.time.Clock()
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
self.surf = pygame.Surface((VIEWPORT_W, VIEWPORT_H))
2021-07-29 02:26:34 +02:00
pygame.transform.scale(self.surf, (SCALE, SCALE))
pygame.draw.rect(self.surf, (255, 255, 255), self.surf.get_rect())
2016-05-03 22:27:42 +03:00
for obj in self.particles:
obj.ttl -= 0.15
2021-07-29 02:26:34 +02:00
obj.color1 = (
int(max(0.2, 0.15 + obj.ttl) * 255),
int(max(0.2, 0.5 * obj.ttl) * 255),
int(max(0.2, 0.5 * obj.ttl) * 255),
2021-07-29 02:26:34 +02:00
)
obj.color2 = (
int(max(0.2, 0.15 + obj.ttl) * 255),
int(max(0.2, 0.5 * obj.ttl) * 255),
int(max(0.2, 0.5 * obj.ttl) * 255),
2021-07-29 02:26:34 +02:00
)
2016-05-03 22:27:42 +03:00
self._clean_particles(False)
for p in self.sky_polys:
scaled_poly = []
for coord in p:
scaled_poly.append((coord[0] * SCALE, coord[1] * SCALE))
pygame.draw.polygon(self.surf, (0, 0, 0), scaled_poly)
gfxdraw.aapolygon(self.surf, scaled_poly, (0, 0, 0))
2016-05-03 22:27:42 +03:00
for obj in self.particles + self.drawlist:
for f in obj.fixtures:
trans = f.body.transform
if type(f.shape) is circleShape:
pygame.draw.circle(
self.surf,
color=obj.color1,
center=trans * f.shape.pos * SCALE,
radius=f.shape.radius * SCALE,
)
pygame.draw.circle(
self.surf,
color=obj.color2,
center=trans * f.shape.pos * SCALE,
radius=f.shape.radius * SCALE,
)
2016-05-03 22:27:42 +03:00
else:
path = [trans * v * SCALE for v in f.shape.vertices]
pygame.draw.polygon(self.surf, color=obj.color1, points=path)
gfxdraw.aapolygon(self.surf, path, obj.color1)
pygame.draw.aalines(
self.surf, color=obj.color2, points=path, closed=True
)
for x in [self.helipad_x1, self.helipad_x2]:
x = x * SCALE
flagy1 = self.helipad_y * SCALE
flagy2 = flagy1 + 50
pygame.draw.line(
self.surf,
color=(255, 255, 255),
start_pos=(x, flagy1),
end_pos=(x, flagy2),
width=1,
)
pygame.draw.polygon(
self.surf,
color=(204, 204, 0),
points=[
(x, flagy2),
(x, flagy2 - 10),
(x + 25, flagy2 - 5),
],
)
gfxdraw.aapolygon(
self.surf,
[(x, flagy2), (x, flagy2 - 10), (x + 25, flagy2 - 5)],
(204, 204, 0),
)
self.surf = pygame.transform.flip(self.surf, False, True)
if self.render_mode == "human":
assert self.screen is not None
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
self.screen.blit(self.surf, (0, 0))
pygame.event.pump()
self.clock.tick(self.metadata["render_fps"])
pygame.display.flip()
elif self.render_mode == "rgb_array":
return np.transpose(
np.array(pygame.surfarray.pixels3d(self.surf)), axes=(1, 0, 2)
2021-07-29 02:26:34 +02:00
)
def close(self):
if self.screen is not None:
import pygame
pygame.display.quit()
pygame.quit()
self.isopen = False
def heuristic(env, s):
"""
The heuristic for
1. Testing
2. Demonstration rollout.
Args:
env: The environment
s (list): The state. Attributes:
s[0] is the horizontal coordinate
s[1] is the vertical coordinate
s[2] is the horizontal speed
s[3] is the vertical speed
s[4] is the angle
s[5] is the angular speed
s[6] 1 if first leg has contact, else 0
s[7] 1 if second leg has contact, else 0
Returns:
a: The heuristic to be fed into the step function defined above to determine the next step and reward.
"""
2021-07-29 02:26:34 +02:00
angle_targ = s[0] * 0.5 + s[2] * 1.0 # angle should point towards center
if angle_targ > 0.4:
angle_targ = 0.4 # more than 0.4 radians (22 degrees) is bad
if angle_targ < -0.4:
angle_targ = -0.4
2021-07-29 15:39:42 -04:00
hover_targ = 0.55 * np.abs(
s[0]
) # target y should be proportional to horizontal offset
2021-07-29 02:26:34 +02:00
angle_todo = (angle_targ - s[4]) * 0.5 - (s[5]) * 1.0
hover_todo = (hover_targ - s[1]) * 0.5 - (s[3]) * 0.5
if s[6] or s[7]: # legs have contact
angle_todo = 0
2021-07-29 15:39:42 -04:00
hover_todo = (
-(s[3]) * 0.5
) # override to reduce fall speed, that's all we need after contact
if env.continuous:
2021-07-29 02:26:34 +02:00
a = np.array([hover_todo * 20 - 1, -angle_todo * 20])
a = np.clip(a, -1, +1)
else:
a = 0
2021-07-29 02:26:34 +02:00
if hover_todo > np.abs(angle_todo) and hover_todo > 0.05:
a = 2
elif angle_todo < -0.05:
a = 3
elif angle_todo > +0.05:
a = 1
return a
2021-07-29 02:26:34 +02:00
def demo_heuristic_lander(env, seed=None, render=False):
total_reward = 0
steps = 0
s, info = env.reset(seed=seed)
while True:
a = heuristic(env, s)
s, r, terminated, truncated, info = step_api_compatibility(env.step(a), True)
total_reward += r
if render:
still_open = env.render()
if still_open is False:
2021-07-29 02:26:34 +02:00
break
if steps % 20 == 0 or terminated or truncated:
print("observations:", " ".join([f"{x:+0.2f}" for x in s]))
print(f"step {steps} total_reward {total_reward:+0.2f}")
steps += 1
if terminated or truncated:
2021-07-29 02:26:34 +02:00
break
if render:
env.close()
return total_reward
class LunarLanderContinuous:
def __init__(self):
raise error.Error(
"Error initializing LunarLanderContinuous Environment.\n"
"Currently, we do not support initializing this mode of environment by calling the class directly.\n"
"To use this environment, instead create it by specifying the continuous keyword in gym.make, i.e.\n"
'gym.make("LunarLander-v2", continuous=True)'
)
2021-07-29 02:26:34 +02:00
if __name__ == "__main__":
demo_heuristic_lander(LunarLander(), render=True)