{"total":91,"rows":[{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","cited_by_count":60,"area":"offlinerl"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43,"area":"offlinerl"},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42,"area":"diffusion"},{"id":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41,"area":"offlinerl"},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18,"area":"offlinerl"},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2311.10747","title":"Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving","created":"2023-10-31","cited_by_count":17,"area":"driving"},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2312.01659","title":"RiskBench: A Scenario-based Benchmark for Risk Identification","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2302.00521","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","created":"2023-02-01","cited_by_count":8,"area":"offlinerl"},{"id":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","cited_by_count":8,"area":"offlinerl"},{"id":"2309.16397","title":"Uncertainty-Aware Decision Transformer for Stochastic Driving Environments","created":"2023-09-28","cited_by_count":8,"area":"driving"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2306.08900","title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","created":"2023-06-15","cited_by_count":7,"area":"offlinerl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2403.01734","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","created":"2024-03-04","cited_by_count":5,"area":"offlinerl"},{"id":"2505.00908","title":"Learning Conservative Neural Control Barrier Functions from Offline Data","created":"2025-05-01","cited_by_count":5,"area":"offlinerl"},{"id":"2512.10822","title":"V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions","created":"2025-12-11","cited_by_count":5,"area":"offlinerl"},{"id":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2501.15085","title":"Data Center Cooling System Optimization Using Offline Reinforcement Learning","created":"2025-01-25","cited_by_count":4,"area":"offlinerl"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2603.15136","title":"Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies","created":"2026-03-16","cited_by_count":4,"area":"offlinerl"},{"id":"2209.09648","title":"Safe Reinforcement Learning with Contrastive Risk Prediction","created":"2022-09-10","cited_by_count":3,"area":null},{"id":"2407.00681","title":"Safe Reinforcement Learning for Power System Control: A Review","created":"2024-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2407.04942","title":"FOSP: Fine-tuning Offline Safe Policy through World Models","created":"2024-07-06","cited_by_count":3,"area":"wm"},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2502.02205","title":"From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control","created":"2025-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","cited_by_count":3,"area":"deeprl"},{"id":"2512.08280","title":"Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making","created":"2025-12-09","cited_by_count":3,"area":"diffusion"},{"id":"2503.20285","title":"Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation","created":"2025-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2602.08054","title":"Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2407.13006","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2509.25727","title":"Boundary-to-Region Supervision for Offline Safe Reinforcement Learning","created":"2025-09-30","cited_by_count":1,"area":"offlinerl"},{"id":"2510.22027","title":"Online Optimization for Offline Safe Reinforcement Learning","created":"2025-10-24","cited_by_count":1,"area":"offlinerl"},{"id":"2602.05776","title":"Cross-Domain Offline Policy Adaptation via Selective Transition Correction","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2605.21225","title":"PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment","created":"2026-05-20","cited_by_count":1,"area":"alignment"},{"id":"2110.10905","title":"Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State Information","created":"2021-10-21","cited_by_count":0,"area":"offlinerl"},{"id":"2209.08947","title":"Age of Semantics in Cooperative Communications: To Expedite Simulation Towards Real via Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":0,"area":"offlinerl"},{"id":"2307.04927","title":"Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2312.14196","title":"Optimizing Heat Alert Issuance with Reinforcement Learning","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2406.03324","title":"UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning","created":"2024-06-05","cited_by_count":0,"area":"offlinerl"},{"id":"2410.18626","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","created":"2024-10-24","cited_by_count":0,"area":"offlinerl"},{"id":"2412.19064","title":"Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding","created":"2024-12-26","cited_by_count":0,"area":null},{"id":"2502.12391","title":"Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL","created":"2025-02-18","cited_by_count":0,"area":"offlinerl"},{"id":"2504.03040","title":"Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards","created":"2025-04-03","cited_by_count":0,"area":"deeprl"},{"id":"2505.01619","title":"Skill-based Safe Reinforcement Learning with Risk Planning","created":"2025-05-02","cited_by_count":0,"area":"deeprl"},{"id":"2505.08179","title":"Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL","created":"2025-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2505.19337","title":"Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies","created":"2025-05-25","cited_by_count":0,"area":"offlinerl"},{"id":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2602.05323","title":"GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.08584","title":"Conditional Sequence Modeling for Safe Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.17312","title":"LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2604.12667","title":"Safe reinforcement learning with online filtering for fatigue-predictive human-robot task planning and allocation in production","created":"2026-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2604.25379","title":"Safe-Support Q-Learning: Learning without Unsafe Exploration","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2604.26516","title":"Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning","created":"2026-04-29","cited_by_count":0,"area":"offlinerl"},{"id":"2605.01356","title":"Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.02777","title":"Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"offlinerl"},{"id":"2605.22376","title":"Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning","created":"2026-05-21","cited_by_count":0,"area":"offlinerl"},{"id":"2606.04749","title":"COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.08312","title":"Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies","created":"2026-06-06","cited_by_count":0,"area":"offlinerl"},{"id":"2606.09559","title":"Safe-RULE: Safe Reinforcement UnLEarning","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2606.14609","title":"Safe Reinforcement Learning of Autonomous Highway Driving: A Unified Framework for Safety and Efficiency","created":"2026-06-12","cited_by_count":0,"area":"driving"},{"id":"2606.21136","title":"Horizon Adaptive Offline Policy Learning via Value Stitching","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2607.03903","title":"CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning","created":"2026-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2608.12306","title":"Redistribution-based Cost Inference Improves Sparse Safe Offline RL","created":"2026-08-12","cited_by_count":0,"area":"offlinerl"},{"id":"2609.12014","title":"Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"offlinerl"},{"id":"2609.34426","title":"Q-learning Penalized Transformer for Safe Offline Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}