sponsors

An open API service aggregating public data about GitHub Sponsors.

farama-foundation

View JSON Representation

The Farama foundation is a nonprofit organization working to develop and maintain open source reinforcement learning tools.

Funding Links: https://github.com/sponsors/Farama-Foundation

GitHub Sponsors Profile

The Farama Foundation is a nonprofit that maintains several key libraries that offer standard APIs in reinforcement learning - Gymnasium for single-agent RL, PettingZoo for multi-agent RL, and Minari for offline RL - along with many of the most used reinforcement learning environments in the field. Our goal is to offer better tools and standardization for reinforcement learning and to make it a more accessible and productive field. Many of our core contributors are the team behind OpenAI Gym. Donations to us go to paying our team to their work on these projects.
You can check out our website at farama.org and join our discord server to meet and interact with our community, as well as ask questions.
We're a registered 501c3 nonprofit organization, meaning that donations to us are deductible on your taxes. For annual donations under $250, can claim this without a receipt. For annual donations over $250, please email us with your name and address and we'll send you a receipt for your taxes.
We also have additional donation tiers geared towards organizational donors that you can view here.

Featured Works

Farama-Foundation/Gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Language: Python - Stars: 7470
Farama-Foundation/PettingZoo

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

Language: Python - Stars: 2655
Farama-Foundation/Minari

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Language: Python - Stars: 298
Farama-Foundation/ViZDoom

Reinforcement Learning environments based on the 1993 game Doom

Language: C++ - Stars: 1747
Farama-Foundation/Minigrid

Simple and easily configurable grid world environments for reinforcement learning

Language: Python - Stars: 2130
Farama-Foundation/Metaworld

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Language: Python - Stars: 1281

Sponsors

Active Sponsors
Past Sponsors

Sponsor Breakdown