Port of Facebook's LLaMA model in C/C++

A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)

Gymnasium for offline reinforcement learning

Gym for multi-agent reinforcement learning

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

An elegant PyTorch deep reinforcement learning library.

Wingman for your AI applications

Open Python 3 API for making your own Smash Bros: Melee AI that works with Slippi Online

A gym-esque environment for Super Smash Bros. Melee.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

A toolkit for developing and comparing reinforcement learning algorithms.

An offline deep reinforcement learning library

Easy-to-use micro-wrappers for Gym and PettingZoo based RL Environments