[ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.

A live stream development of RL tunning for LLM agents

Clean single-file implementation of offline RL algorithms in JAX

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

Latent-based SR using MoE and frequency augmented VAE decoder

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Real-World RL Benchmark Suite

Multi-Joint dynamics with Contact. A general purpose physics simulator.

A toolkit for developing and comparing reinforcement learning algorithms.

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

A library of reinforcement learning components and agents

Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

PyTorch implementations of deep reinforcement learning algorithms and environments