PettingZoo is a standardized API and library for multi-agent reinforcement learning (MARL) environments. It provides a broad set of environments and tools to facilitate the development and evaluation of multi-agent algorithms.
Features
- Provides a unified interface for multi-agent environments
- Includes a diverse collection of MARL benchmarks like classic games and robotics
- Compatible with Gym-style RL libraries
- Supports both simultaneous and sequential action spaces
- Easy-to-use API for creating custom multi-agent environments
- Built-in visualization and rendering options
Categories
Reinforcement Learning LibrariesLicense
MIT LicenseFollow PettingZoo
Other Useful Business Software
Cut Data Warehouse Costs by 54%
BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of PettingZoo!