PettingZoo

multi-agent reinforcement learning environments

Usage

Environments can be interacted with in a manner very similar to Gym:

          
import pettingzoo
env = pettingzoo.knights_archers_zombies_v0.env()
observation = env.reset()
for agent in env.agent_iter():
  reward, done, info = env.last()
  action = policy(observation)
  observation = env.step(action)