ma-gym

A collection of multi agent environments based on OpenAI gym.

Installation

cd ma-gym
pip install -e .

Usage:

import gym
import ma_gym

env = gym.make('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 for complete usage details

Environments:

• Checkers
• Combat
• PredatorPrey
• Pong Duel (two player pong game)
• Switch

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.

Zoo!

Checkers-v0	Switch2-v0	Switch4-v0
PongDuel-v0	Combat-v0	PredatorPrey7x7-v0
PredatorPrey5x5-v0

Testing:

• Install: pip install pytest
• Run: pytest

Acknowledgement:

This project was developed to complement my research internship @ SAS.