method · first seen 6 Oct 2026
off-policy reinforcement learning
Also: off-policy RL
Reinforcement learning that reuses data collected by other policies, such as via replay buffers.
Mentions per week
PapersCodeDiscussion
Earliest sources
- QF3: Fast Flow RL with Filtered Q-GradientsPapers · 6 Oct 2026 · Chung Min Kim, Brent Yi, David McAllister, Hongsuk Choi, Himanshu Gaurav Singh,…
- ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation ModelsPapers · 13 Oct 2026 · Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo
- Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL RegularizationPapers · 13 Oct 2026 · Hao Bai, Jiarui Yao, Tong Zhang
- Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable RewardsPapers · 14 Oct 2026 · Xuanchang Zhang, Tong Zhang
- Echo: Scaling Visual Reinforcement Learning with Off-policy ExperiencePapers · 27 Oct 2026 · Gagan Khandate
- Off-Policy RL with Online Inference Tuning: My Solution to the CoRL 2026 RoboEval ChallengePapers · 8 Nov 2026 · Ilia Larchenko
Latest sources
- Delayed Heuristic-Behavior-Target Coupling for Off-Policy Reinforcement Learning in Inventory ControlPapers · 15 Nov 2026 · Enhui Li, Yuan Cheng, Peiting Han
- ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length ControlPapers · 10 Nov 2026 · Xu Luo, Jiaying Yang, Hao Wu, Junlin Xie, Zijin Hong, Ji Zhang, Lianli Gao, Jing…
- Off-policy Learning with Excursion PoliciesPapers · 9 Nov 2026 · Jiamin He, Mark Rowland, Zhaohan Daniel Guo, Hado van Hasselt, Diana Borsa
- Off-Policy RL with Online Inference Tuning: My Solution to the CoRL 2026 RoboEval ChallengePapers · 8 Nov 2026 · Ilia Larchenko
- Echo: Scaling Visual Reinforcement Learning with Off-policy ExperiencePapers · 27 Oct 2026 · Gagan Khandate
- Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable RewardsPapers · 14 Oct 2026 · Xuanchang Zhang, Tong Zhang
- Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL RegularizationPapers · 13 Oct 2026 · Hao Bai, Jiarui Yao, Tong Zhang
- ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation ModelsPapers · 13 Oct 2026 · Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo
- QF3: Fast Flow RL with Filtered Q-GradientsPapers · 6 Oct 2026 · Chung Min Kim, Brent Yi, David McAllister, Hongsuk Choi, Himanshu Gaurav Singh,…