Farama-Foundation/PettingZoo

Health v2 · maintenance only

Adoption not part of the score

3498 stars · 519 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

PettingZoo is a Python library providing a standard API for multi-agent reinforcement learning environments, analogous to Gymnasium but for multiple agents. It ships with reference environment families (Atari, Butterfly, Classic, SISL) plus wrappers and utilities for MARL research.

Use cases

• train multi-agent reinforcement learning agents
• benchmark MARL algorithms on standard environments
• create custom multi-agent RL environments with a standard API
• run multi-player Atari and board game environments for RL research
• integrate MARL environments with CleanRL, Tianshou, RLlib, or Stable-Baselines3

When to choose

• you need a standardized, well-maintained API for multi-agent RL environments
• you want ready-made reference environments like chess, Hanabi, or cooperative Atari games
• you are doing MARL research and want compatibility with popular RL training libraries

When to avoid

• you only need single-agent RL environments (use Gymnasium instead)
• you need official Windows support
• you need high-performance production simulation rather than research environments

Facets

library · maturity active

reinforcement-learning simulation game-engine testing reinforcement-learning machine-learning artificial-intelligence python multi-agent gymnasium rl-environments marl farama-foundation game-development research linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Farama-Foundation/PettingZoo")