method · first seen 4 Oct 2026
offline reinforcement learning
Also: offline RL, offline learning, offline policy optimization, batch reinforcement learning
Learning a policy from a fixed dataset of previously collected trajectories without further environment interaction.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Pessimistic Minimax Learning for Public-Private Information Games under Unilateral CoveragePapers · 4 Oct 2026 · Shuze Daniel Liu, Claire Chen, Jiuqi Wang, David Simchi-Levi
- Variance-Averse $n$-Step Offline Reinforcement Learning for Sparse Long-Horizon EnvironmentsPapers · 6 Oct 2026 · Guhyeon Kang, Minhae Kwon
- LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RLPapers · 6 Oct 2026 · Songyuan Zhang, Oswin So, Eric Yang Yu, Matthew Cleaveland, Peter Crowley-Dolen,…
- Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous DrivingPapers · 7 Oct 2026 · Mahmoud Selim, Cristina Cipriani, Karl Henrik Johansson
- Q-Learning with Scalar Adjoint MatchingPapers · 7 Oct 2026 · Yonghoon Dong, Minsung Yoon, Jaehyuk Kim, Jungwoo Park, Changyeon Kim, Jinwoo Sh…
- Higher-Order Action Supervision Makes A Strong Policy ClassPapers · 8 Oct 2026 · Peng Cheng, Yunxian Hou, Zhi Zhou, Qian Zhang, Chang Huang, Xianyuan Zhan
Latest sources
- Offline KL-Regularized Reinforcement Learning with Stochastic TransitionsPapers · 12 Nov 2026 · Andrew Liu
- Support-Constrained Offline Policy Improvement for Pediatric ECMO from Limited Clinical DataPapers · 12 Nov 2026 · Fateme Golivand Darvishvand, Saurabh Mathur, Nikhilesh Prabhakar, Michael A. Ski…
- Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process CriticsPapers · 10 Nov 2026 · Marco Chan, Christos Evripidou, Liqiu Dong, Benoit Chachuat, Mehmet Mercangöz
- An Augmented Lagrangian Approach to Lifted Bellman Linear ProgrammingPapers · 10 Nov 2026 · Jongchan Park, Hyukjun Yang, Narim Jeong, Donghwan Lee
- Computationally Efficient Offline Policy Optimization with All-Policy Linear RealizabilityPapers · 8 Nov 2026 · Zhijie Zheng
- Horizon-Scalable Q-LearningPapers · 7 Nov 2026 · Haoran Xu, Pragya Srivastava, Xinjie Liu, Siddhant Agarwal, Amy Zhang
- Bayesian transfer for offline Q-learning with multi-task Gaussian processesPapers · 7 Nov 2026 · Wenxing Guo
- Reinforcement Learning based control of Cancer Chemotherapy treatmentsPapers · 6 Nov 2026 · Jayakody Kankanamalage Chamani Shiranthika
- Compounding Physical RSI: Turning Execution Failure into Inherited CapabilityPapers · 4 Nov 2026 · Yixuan Yang, Qiang Chen, Run Shao, Shuwei Dong, Wenhao Li, Yunpeng Wang, Wenhan…
- Statistical Foundations of Reinforcement Learning: A Non-Asymptotic PerspectivePapers · 30 Oct 2026 · Yuxin Chen, Yuejie Chi, Jianqing Fan, Gen Li, Yuting Wei, Yuling Yan
- KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM AgentsPapers · 30 Oct 2026 · Jinkyeong Choi, Chaebin Jeong, Junsung Jeon, Donghyeon Park
- Generating Critic-Guided Synthetic Experience in Latent World ModelsPapers · 29 Oct 2026 · Jorge de Freitas, Christos Ziakas, Alessandra Russo