mobile handoff for Codex TUI sessions

Post-training with Tinker

A high-performance and light-weight router for vLLM large scale deployment

Bridge Megatron-Core to Hugging Face/Reinforcement Learning

verl: Volcano Engine Reinforcement Learning for LLMs

Making large AI models cheaper, faster and more accessible

Multi-Agent Reinforcement Learning with JAX

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

A customisable 3D platform for agent-based AI research

Rubik's Cube solver in Python

Implementation of Dreamer v3 in pytorch.

Mastering Diverse Domains through World Models

MuZero

Check out the new game server:

A simple OpenAI Gym environment for single and multi-agent reinforcement learning