Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Bingxi Hou, Guochao Jiang, Guofeng Quan +4
Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories.…
cs.LG2025
VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Guochao Jiang, Wenfeng Feng, Guofeng Quan +4
Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning meth…