arXiv 2610.08963 · cs.LG · 2026-10-06
On KL-Regularized Policy Optimization
Yifan Zhang
math-ai
In latest · #236 Added on 2026-10-21
One-line takeaway
KLPO anchors the KL regulariser at the sampling policy to handle stale, mismatched rollouts in asynchronous LLM-agent RL.
KLPO 把 KL 正则锚定在采样策略上，处理异步强化学习中策略过期和推理/训练概率不一致的问题。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Reinforcement learning
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation ▲218
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.