23 KiB
Third-Party Environments
Video Game Environments
ViZDoom
An environment centered around the original Doom game, focusing on visual control (from image to actions) at thousands of frames per second. ViZDoom supports depth and automatic annotation/labels buffers, as well as accessing the sound. The Gym wrappers provide easy-to-use access to the example scenarios that come with ViZDoom. Since 2016, the ViZDoom paper has been cited more than 600 times.
flappy-bird-gym: A Flappy Bird environment for OpenAI Gym
A simple environment for single-agent reinforcement learning algorithms on a clone of Flappy Bird, the hugely popular arcade-style mobile game. Both state and pixel observation environments are available.
gym-derk: GPU accelerated MOBA environment
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
MineRL
Gym interface with Minecraft game focused on a specific sparse reward challenge
Procgen
16 simple-to-use procedurally-generated gym environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizable skills. The environments run at high speed (thousands of steps per second) on a single core.
SlimeVolleyGym: A simple environment for single and multi-agent reinforcement learning
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.
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 Open to PRs of additional games, features, and platforms since gym-retro is no longer maintained
Unity ML Agents
Gym wrappers for arbitrary and premade environments with the Unity game engine.
Classic Environments (board, card, etc. games)
gym-abalone: A two-player abstract strategy board game
An implementation of the board game Abalone.
gym-spoof
Spoof, otherwise known as "The 3-coin game", is a multi-agent (2-player), imperfect-information, zero-sum game.
gym-xiangqi: Xiangqi - The Chinese Chess Game
A reinforcement learning environment of Xiangqi, the Chinese Chess game.
RubiksCubeGym
The RubiksCubeGym package provides environments for twisty puzzles with multiple reward functions to help simulate the methods used by humans.
GymGo
The board game Go, also known as Weiqi. The game that was famously conquered by AlphaGo.
Robotics Environments
GymFC: A flight control tuning and training framework
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 OpenAI environment has been used to generate policies for the world's first open-source neural network flight control firmware Neuroflight.
gym-gazebo
gym-gazebo presents an extension of the initial OpenAI gym for robotics using ROS and Gazebo, an advanced 3D modeling and rendering tool.
gym-goddard: Goddard's Rocket Problem
An environment for simulating the classical optimal control problem where the thrust of a vertically ascending rocket shall be determined such that it reaches the maximum possible altitude while being subject to varying aerodynamic drag, gravity, and mass.
gym-jiminy: training Robots in Jiminy
gym-jiminy presents an extension of the initial OpenAI 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-miniworld
MiniWorld is a minimalistic 3D interior environment simulator for reinforcement learning & robotics research. It can be used to simulate environments with rooms, doors, hallways and various objects (eg: office and home environments, mazes). MiniWorld can be seen as an alternative to VizDoom or DMLab. It is written 100% in Python and designed to be easily modified or extended.
gym-pybullet-drones
A simple environment using PyBullet to simulate the dynamics of a Bitcraze Crazyflie 2.x nanoquadrotor.
MarsExplorer
Mars Explorer is an openai-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
PyBullet based simulations of a robotic arm moving objects.
PyBullet Robotics Environments
3D physics environments like the Mujoco environments but uses the Bullet physics engine and do not require a commercial license. Works on Mac/Linux/Windows.
robo-gym
robo-gym provides a collection of reinforcement learning environments involving robotic tasks applicable in both simulation and real-world robotics.
Offworld-gym
Gym environments that let you control physics robotics in a laboratory via the internet.
Autonomous Driving and Traffic Control Environments
gym-carla
gym-carla provides a gym wrapper for the CARLA simulator, which is a realistic 3D simulator for autonomous driving research. The environment includes a virtual city with several surrounding vehicles running around. Multiple sources of observations are provided for the ego vehicle, such as front-view camera image, lidar point cloud image, and bird-eye view semantic mask. Several applications have been developed based on this wrapper, such as deep reinforcement learning for end-to-end autonomous driving.
gym-duckietown
A lane-following simulator built for the Duckietown project (small-scale self-driving car course).
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
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.
LongiControl
An environment for the stochastic longitudinal control of an electric vehicle. It is intended to be a descriptive and comprehensible example of a continuous real-world problem within the field of autonomous driving.
sumo-rl
Gym wrapper for various environments in the Sumo traffic simulator
CommonRoad-RL
A Gym for solving motion planning problems for various traffic scenarios compatible with CommonRoad benchmarks, which provides configurable rewards, action spaces, and observation spaces.
Multi-Agents
PettingZoo
PettingZoo is a Python library for conducting research in multi-agent reinforcement learning, akin to a multi-agent version of Gym.
Other Environments
anomalous_rl_envs
A set of environments from control tasks: Acrobot, CartPole, and LunarLander with various types of anomalies injected into them. It could be very useful to study the behavior and robustness of a policy.
CARL
Configurable reinforcement learning environments for testing generalization, e.g. CartPole with variable pole lengths or Brax robots with different ground frictions.
CompilerGym
Reinforcement learning environments for compiler optimization tasks, such as LLVM phase ordering, GCC flag tuning, and CUDA loop nest code generation.
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.
Gridworld
The Gridworld package provides grid-based environments to help simulate the results for model-based reinforcement learning algorithms. The initial release supports single agent system only. Some features in this version of the software have become obsolete. New features are being added to the software like windygrid environment.
gym-adserve
An environment that implements a typical multi-armed bandit scenario where an ad server must select the best advertisement to be displayed in a web page. Some example agents included: Random, epsilon-Greedy, Softmax, and UCB1.
gym-algorithmic
These are a variety of algorithmic tasks, such as learning to copy a sequence, present in Gym prior to Gym 0.20.0.
gym-anytrading
AnyTrading is a collection of OpenAI Gym environments for reinforcement learning-based trading algorithms with a great focus on simplicity, flexibility, and comprehensiveness.
gym-autokey
An environment for automated rule-based deductive program verification in the KeY verification system.
gym-ccc
Environments that extend gym's classic control and add many new features including continuous action spaces.
gym-cellular-automata
Environments where the agent interacts with Cellular Automata by changing its cell states.
gym-games
Gym implementations of the MinAtar games, various PyGame Learning Environment games, and various custom exploration games
gym-inventory
gym-inventory is a single-agent domain featuring discrete state and action spaces that an AI agent might encounter in inventory control problems.
gym-maze
A simple 2D maze environment where an agent finds its way from the start position to the goal.
gym-mtsim
MtSim is a general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform.
gym-legacy-toytext
These are the unused toy-text environments present in Gym prior to Gym 0.20.0.
gym-riverswim
A simple environment for benchmarking reinforcement learning exploration techniques in a simplified setting. Hard exploration.
gym-recsys
This package describes an OpenAI Gym interface for creating a simulation environment of reinforcement learning-based recommender systems (RL-RecSys). The design strives for simple and flexible APIs to support novel research.
gym-sokoban
2D Transportation Puzzles. 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.
math-prog-synth-env
In our paper "A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis" we convert the DeepMind Mathematics Dataset into an RL environment based on program synthesis.https://arxiv.org/abs/2107.07373
NASGym
The environment is fully compatible with the OpenAI baselines and exposes a NAS environment following the Neural Structure Code of BlockQNN: Efficient Block-wise Neural Network Architecture Generation. Under this setting, a Neural Network (i.e. the state for the reinforcement learning agent) is modeled as a list of NSCs, an action is the addition of a layer to the network, and the reward is the accuracy after the early-stop training. The datasets considered so far are the CIFAR-10 dataset (available by default) and the meta-dataset (has to be manually downloaded as specified in this repository).
NLPGym: A toolkit to develop RL agents to solve NLP tasks
NLPGym 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.
Obstacle Tower
3D procedurally generated tower where you have to climb to the highest level possible
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.
osim-rl
Musculoskeletal Models in OpenSim. A human musculoskeletal model and a physics-based simulation environment where you can synthesize physically and physiologically accurate motion. One of the environments built in this framework is a competition environment for a NIPS 2017 challenge.
PGE: Parallel Game Engine
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.
QASGym
This is a list of environments for quantum architecture search following the description in Quantum Architecture Search via Deep Reinforcement Learning. The agent designs the quantum circuit by taking actions in the environment. Each action corresponds to a gate applied on some wires. The goal is to build a circuit U that generates the target n-qubit quantum state that belongs to the environment and is hidden from the agent. The circuits are built using Google QuantumAI Cirq.
safe-control-gym
PyBullet based CartPole and Quadrotor environments—with CasADi (symbolic) a priori dynamics and constraints—for learning-based control and model-based reinforcement learning.
VirtualTaobao
An environment for online recommendations, where customers are learned from Taobao.com, one of the world's largest e-commerce platforms.
mo-gym
Multi-objective RL (MORL) gym environments, where the reward is a NumPy array of different (possibly conflicting) objectives.
ABIDES-Gym
ABIDES (Agent-Based Interactive Discrete Event Simulator) is a message-based multi-agent discrete event-based simulator. It enables simulation of complex multi-agent systems for different domains. ABIDES has already supported work in equity markets simulation and federated learning.
ABIDES-Gym (ACM-ICAIF21 publication) is a new wrapper built around ABIDES that enables using ABIDES simulator as an Open AI Gym environment for the training of Reinforcement Learning algorithms.
We apply for this work by specifically using the market's extension of ABIDES/ABIDES-Markets and developing two benchmark financial market Gym environments for training daily investor and execution agents. As a result, these two environments describe classic financial problems with a complex interactive market behavior response to the experimental agent's action.
gym-saturation
An environment for guiding automated theorem provers based on saturation algorithms (e.g. Vampire).
ShinRL
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives (Deep RL Workshop 2021)
racing-rl
reinforcement learning for f1tenth racing
go-explore
Unofficial implementation of the Go-Explore algorithm presented in First return then explore based on stable-baselines3.
tmrl
TrackMania 2020 through RL
racing_dreamer
Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing
racecar_gym
A gym environment for a miniature racecar using the pybullet physics engine.
jiminy
Jiminy: a fast and portable Python/C++ simulator of poly-articulated systems with OpenAI Gym interface for reinforcement learning
evogym-design-tool
Design tool for creating Evolution Gym environments.
l2r
An open-source reinforcement learning environment for autonomous racing.
gym_torcs
Gym-TORCS is the reinforcement learning (RL) environment in TORCS domain with OpenAI-gym-like interface. TORCS is the open-source realistic car racing simulator recently used as an RL benchmark task in several AI studies.
mobile-env
An open, minimalist Gym environment for autonomous coordination in wireless mobile networks.
gym-softrobot
Softrobotics environment package for OpenAI Gym
PyElastica
Python implementation of Elastica, open-source software for the simulation of assemblies of slender, one-dimensional structures using Cosserat Rod theory.
tuxkart-ai
RL agent for the SuperTuxKart game.
ostrichrl
This is the repository accompanying the paper OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion.
quadruped-gym
An OpenAI gym environment for the training of legged robots
Pogo-Stick-Jumping
OpenAI gym environment, testing and evaluation.
evogym
A large-scale benchmark for co-optimizing the design and control of soft robots, as seen in NeurIPS 2021.
iGibson
A Simulation Environment to train Robots in Large Realistic Interactive Scenes
SnakeRL
Repo for Snake RL
starship-landing-gym
A Gym env for propulsive rocket landing.
CompilerGym
Reinforcement learning environments for compiler and program optimization tasks
RaveForce
RaveForce - An OpenAI Gym style toolkit for music generation experiments.
gym-line-follower
Line follower robot simulator environment for Open AI Gym.
DexterousHands
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
OmniIsaacGymEnvs
Reinforcement Learning Environments for Omniverse Isaac Gym
border
A reinforcement learning library in Rust
SpaceRobotEnv
A gym environment designed for free-floating space robot control based on the MuJoCo platform.
gymnax
RL Environments in JAX 🌍