method · first seen 8 Oct 2026
KL regularization
Also: KL penalty, KL anchoring, KL-regularized RL, KL-regularized control, Kullback-Leibler regularization, KL-regularized reinforcement learning
Penalizing divergence from a reference policy during reinforcement learning fine-tuning of language models.
Mentions per week
PapersCodeDiscussion
Rank 190 on 14 Nov 2026 · 6 mentions in 28 days · 5 independent groups · papers · first seen 5 weeks ago · acceleration +1.79
Earliest sources
- When KL Regularization Misfires in Group Policy OptimizationPapers · 8 Oct 2026 · Fei Ding
- Density-Matrix Reinforcement LearningPapers · 12 Oct 2026 · Chiuman Ho
- Fast Rates for Offline Q-Learning with KL RegularizationPapers · 13 Oct 2026 · Yize Hao, Guangxin Jiang, Shuang Qiu
- Your Policy Is Secretly a Harness: The Decision Geometry of Agent InterfacesPapers · 27 Oct 2026 · Jian Mu, Ruibo Shen, Yao Shu
- ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RLPapers · 1 Nov 2026 · Geonwoo Cho, Jaegyun Im, Doyoon Kim, Lexin Li
- iGC: Antibody Optimization via Reinforcement Learning over a Learned Somatic Hypermutation PriorPapers · 3 Nov 2026 · Thao Nguyen, Robert G. Alberstein, Ewa Nowara, Homa MohammadiPeyhani, Holly R. S…
Latest sources
- Offline KL-Regularized Reinforcement Learning with Stochastic TransitionsPapers · 12 Nov 2026 · Andrew Liu
- A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference ResetsPapers · 10 Nov 2026 · Audrey Huang, Nan Jiang, Sham M. Kakade, Sadhika Malladi, Akshay Krishnamurthy,…
- Sharp Sample Complexity of KL-Regularized Reinforcement LearningPapers · 10 Nov 2026 · Andrew Liu
- iGC: Antibody Optimization via Reinforcement Learning over a Learned Somatic Hypermutation PriorPapers · 3 Nov 2026 · Thao Nguyen, Robert G. Alberstein, Ewa Nowara, Homa MohammadiPeyhani, Holly R. S…
- ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RLPapers · 1 Nov 2026 · Geonwoo Cho, Jaegyun Im, Doyoon Kim, Lexin Li
- Your Policy Is Secretly a Harness: The Decision Geometry of Agent InterfacesPapers · 27 Oct 2026 · Jian Mu, Ruibo Shen, Yao Shu
- Fast Rates for Offline Q-Learning with KL RegularizationPapers · 13 Oct 2026 · Yize Hao, Guangxin Jiang, Shuang Qiu
- Density-Matrix Reinforcement LearningPapers · 12 Oct 2026 · Chiuman Ho
- When KL Regularization Misfires in Group Policy OptimizationPapers · 8 Oct 2026 · Fei Ding