mlsanityData to 7 Oct 2026

Safe offline RL

115 papers0 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: safe, safety, offline, policy, surgical

Key facts. Safe offline RL: 115 papers on arXiv since 2019 (data through 7 Oct 2026). 21 of its 115 mapped papers (18%) cite “Constraints Penalized Q-learning for Safe Offline Reinforcement Learning” (2021, arXiv 2107.09003). 16 of its 115 mapped papers (14%) cite “Datasets and Benchmarks for Offline Safe Reinforcement Learning” (2023, arXiv 2306.09303). 1 new paper 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

1 new since 17 Sep

  1. Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination

Foundations

Most cited by papers here

  1. Constraints Penalized Q-learning for Safe Offline Reinforcement Learning2021cited by 21 here
  2. Datasets and Benchmarks for Offline Safe Reinforcement Learning2023cited by 16 here
  3. Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model2024cited by 15 here
  4. Constrained Decision Transformer for Offline Safe Reinforcement Learning2023cited by 14 here
  5. Safe Offline Reinforcement Learning with Real-Time Budget Constraints2023cited by 9 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2019Behavior Regularized Offline Reinforcement Learningcited by 11 here
  2. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 11 here
  3. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 28 here
  4. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 7 here
  5. 2020MOPO: Model-based Offline Policy Optimizationcited by 6 here
  6. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 19 here
  7. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 17 here
  8. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 20 here
  9. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 5 here
  10. 2023Constrained Decision Transformer for Offline Safe Reinforcement Learningcited by 14 here
  11. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 16 here
  12. 2024Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Modelcited by 15 here
12 more it builds on, not in this chain
  1. 2018Behavioral Cloning from Observationcited by 5 here
  2. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 5 here
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 36 here
  4. 2021Offline Reinforcement Learning with Fisher Divergence Critic Regularizationcited by 7 here
  5. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 8 here
  6. 2021OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimationcited by 12 here
  7. 2021Constraints Penalized Q-learning for Safe Offline Reinforcement Learningcited by 21 here
  8. 2021Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settingscited by 5 here
  9. 2022Mildly Conservative Q-Learning for Offline Reinforcement Learningcited by 5 here
  10. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 8 here
  11. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 7 here
  12. 2023Safe Offline Reinforcement Learning with Real-Time Budget Constraintscited by 9 here

The 24 most cited of 244.

Browse

30 of 115, ranked 6–35

  1. 6Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks20245
  2. 7OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning20245
  3. 8Offline Safe Reinforcement Learning Using Trajectory Classification20245
  4. 9SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning20235
  5. 10Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings20215
  6. 11SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning20254
  7. 12Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning20244
  8. 13Learning Control Barrier Functions from Expert Demonstrations20204
  9. 14V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions20253
  10. 15Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning20243
All 30
  1. 16FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning20243
  2. 17Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration20233
  3. 18Learning from Demonstrations for Autonomous Soft-tissue Retraction20213
  4. 19Advancing Safe Mechanical Ventilation Using Offline RL With Hybrid Actions and Clinically Aligned Rewards20252
  5. 20SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems20242
  6. 21Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications20232
  7. 22Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects20232
  8. 23Semi-Markov Offline Reinforcement Learning for Healthcare20222
  9. 24Offline Reinforcement Learning for Safer Blood Glucose Control in People with Type 1 Diabetes20222
  10. 25End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions20222
  11. 26The hidden risks of temporal resampling in clinical reinforcement learning20261
  12. 27Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning20261
  13. 28OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories20261
  14. 29Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning20261
  15. 30PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment20261
  16. 31Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies20251
  17. 32Boundary-to-Region Supervision for Offline Safe Reinforcement Learning20251
  18. 33Exploring Time-Step Size in Reinforcement Learning for Sepsis Treatment20251
  19. 34SurgiPose: Estimating Surgical Tool Kinematics from Monocular Video for Surgical Robot Learning20251
  20. 35Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination20241