OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Pettingzoo

PettingZoo is an open-source Python library that provides a standard API and reference environments for multi-agent reinforcement-learning research. Its Agent Environment Cycle API supports turn-based agent interaction, and a parallel API is available for environments where agents act simultaneously.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pettingzoo — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use PettingZoo when a research or development workflow needs a Python interface for multi-agent environments, whether using a reference scenario or creating a custom one.

Who it is for

  • Researchers developing or evaluating multi-agent reinforcement-learning methods.
  • Developers building custom multi-agent environments or training workflows.

Documented uses

  • Use a shared interface to interact with multi-agent environments.
  • Explore cooperative, competitive and mixed-sum reference scenarios.
  • Create custom environments using the project’s tutorials and examples.
  • Build training workflows with external libraries featured in PettingZoo tutorials.
Before you choose

Requirements & limits

The repository is public and licensed under MIT. The project supports and maintains Linux and macOS; Windows is not officially supported.

  • Choose the Agent Environment Cycle API for turn-based interaction; use the parallel API when the environment supports simultaneous actions.
  • Environment families may require separate dependency extras; the base package does not install all family dependencies.
  • PettingZoo supplies environments and interfaces, while training examples use external libraries such as CleanRL, Tianshou and AgileRL.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install PettingZoo and environment-family dependencies

Set up the base library and add dependencies for one environment family or all families.

Before you start

  • Python with pip
  • Linux or macOS for officially supported and maintained use

Steps

  1. Install the base package with the command below.

    Documented command
    pip install pettingzoo

  2. For one family, install its extra, such as the command below; to install dependencies for all families, use the command below.

    Documented command
    pip install 'pettingzoo[atari]'
    Documented command
    pip install 'pettingzoo[all]'

Expected outcome

The base PettingZoo library is installed, with dependency extras requested for the selected environment family or all families.

Guide limitations

  • The base installation does not include dependencies for every environment family.
  • Some environments can be problematic to install on certain systems.
  • Windows contributions are accepted, but Windows is not officially supported.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Farama-Foundation/PettingZoo · Official homepage title · retained in its source language
How we review sourcesSuggest a correction