Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/koulanurag/ma-gym
A collection of multi agent environments based on OpenAI gym.
https://github.com/koulanurag/ma-gym
collaborative environment gym multi-agent openai-gym reinforcement-learning
Last synced: about 1 month ago
JSON representation
A collection of multi agent environments based on OpenAI gym.
- Host: GitHub
- URL: https://github.com/koulanurag/ma-gym
- Owner: koulanurag
- License: apache-2.0
- Created: 2019-06-10T15:28:41.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2024-07-07T15:52:18.000Z (5 months ago)
- Last Synced: 2024-10-02T00:12:58.315Z (2 months ago)
- Topics: collaborative, environment, gym, multi-agent, openai-gym, reinforcement-learning
- Language: Python
- Homepage: https://github.com/koulanurag/ma-gym/wiki
- Size: 3.87 MB
- Stars: 559
- Watchers: 7
- Forks: 99
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-deep-rl - ma-gym - A collection of multi agent environments based on OpenAI gym. (Environments)
- awesome-marl-engineering - ma-gym - marl](https://github.com/koulanurag/minimal-marl), set of baselines for vanilla MARL problems by Anurag Koul (Engineering / Building Multi-agent Environments)
README
# ma-gym
It's a collection of multi agent environments based on OpenAI gym. Also, you can use [**minimal-marl**](https://github.com/koulanurag/minimal-marl) to warm-start training of agents.
[](https://pepy.tech/project/ma-gym)
[](https://github.com/koulanurag/ma-gym/wiki)
[](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=14123576959169220642,12284637994392993807)
[](https://colab.research.google.com/github/koulanurag/ma-gym/blob/master/examples/colab_example.ipynb)
## Installation
- Setup (important):
```bash
pip install 'pip<24.1'
pip install 'setuptools<=66'
pip install 'wheel<=0.38.4'
```
- Install package:
- Using PyPI:
```bash
pip install ma-gym
```
- Directly from source (recommended):
```bash
git clone https://github.com/koulanurag/ma-gym.git
cd ma-gym
pip install -e .
```
## Reference:
Please use this bibtex if you would like to cite it:
```
@misc{magym,
author = {Koul, Anurag},
title = {ma-gym: Collection of multi-agent environments based on OpenAI gym.},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/koulanurag/ma-gym}},
}
```
## Usage:
```python
import gym
env = gym.make('ma_gym:Switch2-v0')
done_n = [False for _ in range(env.n_agents)]
ep_reward = 0
obs_n = env.reset()
while not all(done_n):
env.render()
obs_n, reward_n, done_n, info = env.step(env.action_space.sample())
ep_reward += sum(reward_n)
env.close()
```
Please refer to [**Wiki**](https://github.com/koulanurag/ma-gym/wiki/Usage) for complete usage details
## Environments:
- [x] Checkers
- [x] Combat
- [x] PredatorPrey
- [x] Pong Duel ```(two player pong game)```
- [x] Switch
- [x] Lumberjacks
- [x] TrafficJunction
```
Note : openai's environment can be accessed in multi agent form by prefix "ma_".Eg: ma_CartPole-v0
This returns an instance of CartPole-v0 in "multi agent wrapper" having a single agent.
These environments are helpful during debugging.
```
Please refer to [Wiki](https://github.com/koulanurag/ma-gym/wiki/Environments) for more details.
## Zoo!
| __Checkers-v0__ | __Combat-v0__ | __Lumberjacks-v0__ |
|:---:|:---:|:---:|
||||
| __PongDuel-v0__ | __PredatorPrey5x5-v0__ | __PredatorPrey7x7-v0__ |
|  |  |  |
| __Switch2-v0__ | __Switch4-v0__ | __TrafficJunction4-v0__ | |
|  | ||
| __TrafficJunction10-v0__ |
|| | |
## Testing:
- Install: ```pip install -e ".[test]" ```
- Run: ```pytest```
## Acknowledgement:
- This project was initially developed to complement my research internship @ [SAS](https://www.sas.com/en_us/home.html) (Summer - 2019).