Skip to content

Commit 8c167b8

Browse files
authored
Update third party environments (#395)
1 parent 2a9077b commit 8c167b8

File tree

1 file changed

+68
-27
lines changed

1 file changed

+68
-27
lines changed

Diff for: docs/environments/third_party_environments.md

+68-27
Original file line numberDiff line numberDiff line change
@@ -2,20 +2,84 @@
22
:tocdepth: 2
33
```
44

5-
# Third-party Environments
5+
# Third-Party Environments
66

7-
There are a number of Reinforcement Learning environments built by authors not included with Gymnasium. The Farama Foundation maintains a number of projects for gridworlds, procedurally generated worlds, video games, robotics, these can be found at [projects](https://farama.org/projects).
7+
The Farama Foundation maintains a number of other [projects](https://farama.org/projects), most of which use Gymnasium. Topics include:
8+
multi-agent RL ([PettingZoo](https://pettingzoo.farama.org/)),
9+
offline-RL ([Minari](https://minari.farama.org/)),
10+
gridworlds ([Minigrid](https://minigrid.farama.org/)),
11+
robotics ([Gymnasium-Robotics](https://robotics.farama.org/)),
12+
multi-objective RL ([MO-Gymnasium](https://mo-gymnasium.farama.org/))
13+
many-agent RL ([MAgent2](https://magent2.farama.org/)),
14+
3D navigation ([Miniworld](https://miniworld.farama.org/)), and many more.
815

9-
## Video Game environments
16+
*This page contains environments which are not maintained by Farama Foundation and, as such, cannot be guaranteed to function as intended.*
17+
18+
*If you'd like to contribute an environment, please reach out on [Discord](https://discord.gg/nHg2JRN489).*
19+
20+
### [highway-env: Autonomous driving and tactical decision-making tasks](https://github.com/eleurent/highway-env)
21+
22+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.27.1-blue)]()
23+
[![GitHub stars](https://img.shields.io/github/stars/eleurent/highway-env)]()
24+
25+
An environment for behavioral planning in autonomous driving, with an emphasis on high-level perception and decision rather than low-level sensing and control.
26+
27+
### [sumo-rl: Reinforcement Learning using SUMO traffic simulator](https://github.com/LucasAlegre/sumo-rl)
28+
29+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.26.3-blue)]()
30+
[![GitHub stars](https://img.shields.io/github/stars/LucasAlegre/sumo-rl)]()
31+
32+
Gymnasium wrapper for various environments in the SUMO traffic simulator. Supports both single and multiagent settings (using [pettingzoo](https://pettingzoo.farama.org/)).
33+
34+
### [panda-gym: Robotics environments using the PyBullet physics engine](https://github.com/qgallouedec/panda-gym/)
35+
36+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.26.3-blue)]()
37+
[![GitHub stars](https://img.shields.io/github/stars/qgallouedec/panda-gym)]()
38+
39+
PyBullet based simulations of a robotic arm moving objects.
40+
41+
### [tmrl: TrackMania 2020 through RL](https://github.com/trackmania-rl/tmrl/)
42+
43+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.27.1-blue)]()
44+
[![GitHub stars](https://img.shields.io/github/stars/trackmania-rl/tmrl)]()
45+
46+
tmrl is a distributed framework for training Deep Reinforcement Learning AIs in real-time applications. It is demonstrated on the TrackMania 2020 video game.
47+
48+
### [Safety-Gymnasium: Ensuring safety in real-world RL scenarios](https://github.com/PKU-MARL/safety-gymnasium)
49+
50+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.26.3-blue)]()
51+
[![GitHub stars](https://img.shields.io/github/stars/PKU-MARL/safety-gymnasium)]()
52+
53+
Highly scalable and customizable Safe Reinforcement Learning library.
1054

1155
### [stable-retro: Classic retro games, a maintained version of OpenAI Retro](https://github.com/MatPoliquin/stable-retro)
1256

13-
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
57+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.27.1-blue)]()
58+
[![GitHub stars](https://img.shields.io/github/stars/MatPoliquin/stable-retro)]()
59+
60+
Supported fork of gym-retro: turn classic video games into Gymnasium environments.
1461

1562
### [flappy-bird-gymnasium: A Flappy Bird environment for Gymnasium](https://github.com/markub3327/flappy-bird-gymnasium)
1663

64+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.27.1-blue)]()
65+
[![GitHub stars](https://img.shields.io/github/stars/markub3327/flappy-bird-gymnasium)]()
66+
1767
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.
1868

69+
### [matrix-mdp: Easily create discrete MDPs](https://github.com/Paul-543NA/matrix-mdp-gym)
70+
71+
[![Gymnasium version dependency](https://img.shields.io/badge/Gymnasium-v0.26.2-blue)]()
72+
[![GitHub stars](https://img.shields.io/github/stars/Paul-543NA/matrix-mdp-gym)]()
73+
74+
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.
75+
76+
# Third-Party Environments using Gym
77+
78+
There are a large number of third-party environments using various versions of [Gym](https://github.com/openai/gym).
79+
Many of these can be adapted to work with gymnasium (see [Compatibility with Gym](https://gymnasium.farama.org/content/gym_compatibility/)), but are not guaranteed to be fully functional.
80+
81+
## Video Game environments
82+
1983
### [gym-derk: GPU accelerated MOBA environment](https://gym.derkgame.com/)
2084

2185
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
@@ -46,9 +110,6 @@ A simple environment using [PyBullet](https://github.com/bulletphysics/bullet3)
46110

47111
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.
48112

49-
### [panda-gym: Robotics environments using the PyBullet physics engine](https://github.com/qgallouedec/panda-gym/)
50-
51-
PyBullet based simulations of a robotic arm moving objects.
52113

53114
### [robo-gym: Real-world and simulation robotics](https://github.com/jr-robotics/robo-gym)
54115

@@ -80,10 +141,6 @@ Reinforcement Learning Environments for Omniverse Isaac Gym
80141

81142
## Autonomous Driving environments
82143

83-
### [sumo-rl](https://github.com/LucasAlegre/sumo-rl)
84-
85-
Gym wrapper for various environments in the Sumo traffic simulator
86-
87144
### [gym-duckietown](https://github.com/duckietown/gym-duckietown)
88145

89146
A lane-following simulator built for the [Duckietown](http://duckietown.org/) project (small-scale self-driving car course).
@@ -92,18 +149,10 @@ A lane-following simulator built for the [Duckietown](http://duckietown.org/) pr
92149

93150
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.
94151

95-
### [highway-env](https://github.com/eleurent/highway-env)
96-
97-
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.
98-
99152
### [CommonRoad-RL](https://commonroad.in.tum.de/tools/commonroad-rl)
100153

101154
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.
102155

103-
### [tmrl: TrackMania 2020 through RL](https://github.com/trackmania-rl/tmrl/)
104-
105-
tmrl is a distributed framework for training Deep Reinforcement Learning AIs in real-time applications. It is demonstrated on the TrackMania 2020 video game.
106-
107156
### [racing_dreamer](https://github.com/CPS-TUWien/racing_dreamer/)
108157

109158
Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing
@@ -126,14 +175,6 @@ Reinforcement learning environments for compiler optimization tasks, such as LLV
126175

127176
Configurable reinforcement learning environments for testing generalization, e.g. CartPole with variable pole lengths or Brax robots with different ground frictions.
128177

129-
### [matrix-mdp: Easily create discrete MDPs](https://github.com/Paul-543NA/matrix-mdp-gym)
130-
131-
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.
132-
133-
### [mo-gym: Multi-objective Reinforcement Learning environments](https://github.com/LucasAlegre/mo-gym)
134-
135-
Multi-objective RL (MORL) gym environments, where the reward is a NumPy array of different (possibly conflicting) objectives.
136-
137178
### [gym-cellular-automata: Cellular Automata environments](https://github.com/elbecerrasoto/gym-cellular-automata)
138179

139180
Environments where the agent interacts with _Cellular Automata_ by changing its cell states.

0 commit comments

Comments
 (0)