Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Paper • 2609.32444 • Published • 35
Shangzhe Li
DVA13304
AI & ML interests
Reinforcement Learning, Imitation Learning, Learning Theory
Recent Activity
authored a paper 8 days ago
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It authored a paper 8 days ago
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM ReasoningOrganizations
None yet