Awesome Open Source
Awesome Open Source


A collection of multi agent environments based on OpenAI gym.

Python package Upload Python Package


Using PyPI:

pip install ma-gym

Directly from source:

git clone
cd ma-gym
pip install -e .


Please use this bibtex if you would like to cite it:

      author = {Koul, Anurag},
      title = {ma-gym: Collection of multi-agent environments based on OpenAI gym.},
      year = {2019},
      publisher = {GitHub},
      journal = {GitHub repository},
      howpublished = {\url{}},


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):
    obs_n, reward_n, done_n, info = env.step(env.action_space.sample())
    ep_reward += sum(reward_n)

Please refer to Wiki for complete usage details


  • [x] Checkers
  • [x] Combat
  • [x] PredatorPrey
  • [x] Pong Duel (two player pong game)
  • [x] Switch
  • [x] Lumberjacks
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 for more details.


Checkers-v0 Combat-v0 Lumberjacks-v0
Checkers-v0.gif Combat-v0.gif Lumberjacks-v0.gif
PongDuel-v0 PredatorPrey5x5-v0 PredatorPrey7x7-v0
PongDuel-v0.gif PredatorPrey5x5-v0.gif PredatorPrey7x7-v0.gif
Switch2-v0 Switch4-v0
Switch2-v0.gif Switch4-v0.gif


  • Install: pip install -e ".[test]"
  • Run: pytest


  • This project was initially developed to complement my research internship @ SAS (Summer - 2019).

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (52,053
reinforcement-learning (546
openai-gym (68
environment (63
gym (47
collaborative (21

Find Open Source By Browsing 7,000 Topics Across 59 Categories