Implementation of Evolutionary Strategies with Multi-Agent Deep Reinforcement Learning in PettingZoo Environments
Description: Simple Training and Evaluation of Multi-Agent Environments with Deep Reinforcement Algorithms.
Supports Python 3.6, 3.7, 3.8, and 3.9 on Linux and macOS, however currently the Windows support is not avalable.
pip install pettingzoo[all]pip install supersuitVisit Github for more details about SuperSuit.
All requirements could be installed with:
pip install -r requirements.txtEnvironments in PettingZoo (Github)
- Atari: Multi-player Atari 2600 games (cooperative, competitive and mixed sum)
- Butterfly: Cooperative graphical games developed by us, requiring a high degree of coordination
- Classic: Classical games including card games, board games, etc.
- MAgent: Configurable environments with massive numbers of particle agents, originally from https://github.com/geek-ai/MAgent
- MPE: A set of simple nongraphical communication tasks, originally from https://github.com/openai/multiagent-particle-envs
- SISL: 3 cooperative environments, originally from https://github.com/sisl/MADRL