Rl

An elegant PyTorch deep reinforcement learning library.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!

Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Distributed RL System for LLM Reasoning

TTRL: Test-Time Reinforcement Learning

AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.

🔁 AMP-RSL-RL: Adversarial Motion Priors for robotic RL (PPO + motion imitation)

Multi-Objective Reinforcement Learning algorithms implementations.

Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"

A repo for open research on building large reasoning models

reasoning model trained using GRPO towards rosetta REF2015 for protein stability

基于gym的pytorch深度强化学习(DRL)(PPO,PPG,DQN,SAC,DDPG,TD3等算法)

OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement

Machine learning library, Distributed training, Deep learning, Reinforcement learning, Models, TensorFlow, PyTorch