Home Projects PettingZoo
PettingZoo
Python

PettingZoo

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

by Farama-Foundation · GitHub
Stars
Forks
Created
Last commit
Category
Language
apigymnasiummulti-agent-reinforcement-learningPython
View on GitHub
In plain words

Research and test multi-agent learning scenarios using a standard set of environments.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
PettingZoo — GitHub preview card
📈 Star history
3 4713 469
2026-07-152026-08-31
📈 Track PettingZoo

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

PettingZoo has 3.5k stars on GitHub. It has been forked 511 times. PettingZoo is written mainly in Python. It has been in active development since 2020. Its main topics are api, gymnasium, multi-agent-reinforcement-learning, multiagent-reinforcement-learning.

Frequently asked questions

What is PettingZoo?

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Is PettingZoo open source?

PettingZoo is an open-source project.

Is PettingZoo free?

Yes. PettingZoo is free and open source — you can use, modify and self-host it.

What language is PettingZoo written in?

PettingZoo is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — PettingZoo

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=farama-foundation-pettingzoo)](https://olud.ai/project/farama-foundation-pettingzoo.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.