farama-foundation Goto Github PK

a2perf

A2Perf is a benchmark for evaluating agents on sequential decision problems that are relevant to the real world. This repository contains code for running and evaluating participant's submissions on the benchmark platform.

a2perf-benchmark-submission

a2perf-circuit-training

a2perf-code-carbon

a2perf-quadruped-locomotion

a2perf-reliability-metrics

a2perf-web-nav

arcade-learning-environment

The Arcade Learning Environment (ALE) -- a platform for AI research.

autorom

A tool to automate installing Atari ROMs for the Arcade Learning Environment

celshast

chatarena

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

crowdplay

A web based platform for collecting human actions in reinforcement learning environments

d4rl

A collection of reference environments for offline reinforcement learning

d4rl-evaluations

farama-notifications

Allows for providing notifications on import to all Farama Packages

farama.org

gym-docs

Code for Gym documentation website

gym-examples

Example code for the Gym documentation

gym-notices

gymnasium

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

gymnasium-env-template

A template gymnasium environment for users to build upon

gymnasium-notices

gymnasium-robotics

A collection of robotics simulation environments for reinforcement learning

hanabi-learning-environment

hanabi_learning_environment is a research platform for Hanabi experiments.

highwayenv

A minimalist environment for decision-making in autonomous driving

jumpy

On-the-fly conversions between Jax and NumPy tensors

lycon2

A minimal and fast image library for Python and C++

magent

An engine to create high performance multi-agent grid world environments with hundreds or thousands of agents, along with a set of reference environments

magent2

An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments

metaworld

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