Third-Party Environments¶
These environments are not maintained by Farama Foundation and, as such, cannot be guaranteed to function as intended.
Environments using the latest versions of PettingZoo¶
Due to a very recent major release of PettingZoo, there are currently few contributed third-party environments. If you’d like to contribute one, please reach out on Discord.
Sumo-RL¶
PettingZoo (and Gymnasium) wrappers for the widely used SUMO traffic simulation.
POGEMA¶
Partially-Observable Grid Environment for Multiple Agents (POGEMA) is a grid-based environment that was specifically designed to be flexible, tunable and scalable.
Racecar Gym¶
A multi-agent racing environment for a miniature, F1Tenth-like racecar using the Bullet physics engine with PyBullet.
Teamfight Tactics MuZero Agent¶
Using Google DeepMind’s MuZero algorithm to learn to play Teamfight Tactics, an auto chess game made by Riot games.
CookingZoo¶
CookingZoo: a gym-cooking derivative to simulate a complex cooking environment.
Crazy-RL¶
A library for doing reinforcement learning using Crazyflie drones.
DSSE: Drone Swarm Search Environment¶
A single and multi-agent environment to train swarms of drones for maritime search.
PettingZoo Dilemma Envs¶
PettingZoo environments for classic game theory problems: Prisoner’s Dilemma, Samaritan’s Dilemma, Stag Hunt, Chicken and Matching Pennies.
Breakout-Clone¶
Modernized clone of the Breakout arcade game, using Unity game engine and PettingZoo.
Online playable game (using Unity WebGL and Unity ML-Agents): link, tutorial
Carla Gym¶
PettingZoo interface for CARLA Autonomous Driving simulator.
MATS Gym¶
A multi-agent traffic scenario environment for CARLA that supports ScenarioRunner, OpenScenario and Scenic scenario descriptions. It is also compatible with the CARLA Autonomous Driving Challenge.
Fanorona AEC¶
Implementation of the board game Fanorona.
Gobblet-RL¶
Interactive PettingZoo implementation of the Gobblet board game.
Online game demo (using Pygame WebAssembly): link, tutorial
Cathedral-RL¶
Interactive PettingZoo implementation of the Cathedral board game.
Interactive Connect Four¶
Play Connect Four in real-time against an RLlib agent trained via self-play and PPO.
Online game demo (using Gradio and HuggingFace Spaces): link, tutorial
Environments using older versions of PettingZoo¶
The following environments use a now-depreciated API design for PettingZoo, so may be more difficult to use.
Neural MMO¶
Massively multiagent environment, inspired by Massively Multiplayer Online (MMO) role-playing games.
Sequential Social Dilemma Games¶
An open-source implementation of DeepMind’s Sequential Social Dilemma (SSD) multi-agent game-theoretic environments [1].
Note: DeepMind’s recently released Meltingpot includes these scenarios and many more, and can be used with PettingZoo via a Shimmy conversion wrapper.
Kaggle Environments¶
Environments for Kaggle machine learning challenges.
cogment-verse¶
Library of Environments, Human Actor UIs and Agent implementation for Human In the Loop Learning & Reinforcement Learning.
Stone Ground Hearth Battles¶
Simulator and environments for Blizzard’s popular card game Hearthstone Grounds, including bots and human-interaction.
Cyber Operations Research Gym¶
A cyber-security research environment for training and development of security human and autonomous agents.
conflict_rez¶
Conflict resolution for multiple vehicles in confined spaces.
pz-battlesnake¶
PettingZoo environment for online multi-player game Battlesnake.
BomberManAI¶
Environment with a simplified version of the video game BomberMan.
Galaga AI¶
Implementation of the Galaga arcade game using Unity game engine and Unity ML-Agents.
skyjo_rl¶
Implementation of the board game SkyJo.
Mu Torere¶
Implementation of the board game Mū tōrere from New Zealand.