Lin Yan

Risk-Sensitive Reinforcement Learning for Alleviating Exploration Dilemmas in Large Language Models

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier

Process Supervision-Guided Policy Optimization for Code Generation

Truncated Proximal Policy Optimization

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Process Supervision-Guided Policy Optimization for Code Generation

Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization