GRPO

Get Started

• Get Started
  • GRPO

Developer Guide

• Developer Guide
  • Multi-turn Training
  • Multi-Task Training
  • Reward Function
  • Reward Model
  • GYM Environment Training

Advanced Research

• Advanced Research
  • Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
  • DAPO
  • DeepEyes: Incentivizing “Thinking with Images” via Reinforcement Learning
  • Group Sequence Policy Optimization
  • On-Policy RL Meets Off-Policy Experts: Harmonizing SFT and RL via Dynamic Weighting (CHORD)