{"total":125,"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":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"area":"alignment"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"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":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2302.14372","title":"The In-Sample Softmax for Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":33,"area":"offlinerl"},{"id":"2505.00779","title":"Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures","created":"2025-05-01","cited_by_count":33,"area":"wm"},{"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":"2402.04080","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","created":"2024-02-06","cited_by_count":31,"area":"diffusion"},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2306.12755","title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning","created":"2023-06-22","cited_by_count":27,"area":"offlinerl"},{"id":"2310.11971","title":"Improving Generalization of Alignment with Human Preferences through Group Invariant Learning","created":"2023-10-18","cited_by_count":25,"area":"alignment"},{"id":"2405.08740","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","created":"2024-05-14","cited_by_count":25,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"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":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20,"area":"offlinerl"},{"id":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2502.04778","title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning","created":"2025-02-07","cited_by_count":20,"area":"diffusion"},{"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":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18,"area":"offlinerl"},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17,"area":"offlinerl"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2312.07685","title":"A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning","created":"2023-12-12","cited_by_count":15,"area":"offlinerl"},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2310.05422","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":12,"area":"offlinerl"},{"id":"2206.06841","title":"Robust Reinforcement Learning with Distributional Risk-averse formulation","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"id":"2405.17031","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":10,"area":"offlinerl"},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2302.06884","title":"Conservative State Value Estimation for Offline Reinforcement Learning","created":"2023-02-14","cited_by_count":9,"area":"offlinerl"},{"id":"2312.03991","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","created":"2023-12-07","cited_by_count":9,"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":"2306.14479","title":"Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization","created":"2023-06-26","cited_by_count":8,"area":"offlinerl"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"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":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","cited_by_count":8,"area":"offlinerl"},{"id":"2510.03988","title":"The Signal is in the Steps: Local Scoring for Reasoning Data Selection","created":"2025-10-05","cited_by_count":8,"area":"distill"},{"id":"2602.02900","title":"Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning","created":"2026-02-02","cited_by_count":8,"area":"offlinerl"},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2306.08900","title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","created":"2023-06-15","cited_by_count":7,"area":"offlinerl"},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2405.11206","title":"Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses","created":"2024-05-18","cited_by_count":7,"area":"offlinerl"},{"id":"2407.04285","title":"Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling","created":"2024-07-05","cited_by_count":7,"area":"offlinerl"},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2307.02752","title":"Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-07-06","cited_by_count":6,"area":"offlinerl"},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5,"area":"offlinerl"},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2307.08840","title":"Bayesian Safe Policy Learning with Chance Constrained Optimization: Application to Military Security Assessment during the Vietnam War","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","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":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2301.13152","title":"STEEL: Singularity-aware Reinforcement Learning","created":"2023-01-30","cited_by_count":3,"area":"offlinerl"},{"id":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","cited_by_count":3,"area":"offlinerl"},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2306.15503","title":"Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning","created":"2023-06-27","cited_by_count":3,"area":"offlinerl"},{"id":"2310.17245","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","created":"2023-10-26","cited_by_count":3,"area":"offlinerl"},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3,"area":"offlinerl"},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2412.03258","title":"Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning","created":"2024-12-04","cited_by_count":3,"area":"offlinerl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2602.19917","title":"Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning","created":"2026-02-23","cited_by_count":3,"area":"offlinerl"},{"id":"2210.10469","title":"Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation","created":"2022-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2312.17168","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","created":"2023-12-28","cited_by_count":2,"area":"offlinerl"},{"id":"2401.02914","title":"A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty","created":"2024-01-05","cited_by_count":2,"area":"deeprl"},{"id":"2404.04682","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","created":"2024-04-06","cited_by_count":2,"area":"offlinerl"},{"id":"2406.04088","title":"Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning","created":"2024-06-06","cited_by_count":2,"area":"offlinerl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2503.20285","title":"Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation","created":"2025-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2504.01719","title":"Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning","created":"2025-04-02","cited_by_count":2,"area":"offlinerl"},{"id":"2504.11944","title":"VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning","created":"2025-04-16","cited_by_count":2,"area":"offlinerl"},{"id":"2505.01822","title":"Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning","created":"2025-05-03","cited_by_count":2,"area":"diffusion"},{"id":"2505.23871","title":"ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning","created":"2025-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2511.02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","created":"2025-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2211.01471","title":"Dual Generator Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2404.02545","title":"Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning","created":"2024-04-03","cited_by_count":1,"area":"offlinerl"},{"id":"2405.07223","title":"Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning","created":"2024-05-12","cited_by_count":1,"area":"offlinerl"},{"id":"2502.11480","title":"Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective","created":"2025-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2505.05126","title":"Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach","created":"2025-05-08","cited_by_count":1,"area":"offlinerl"},{"id":"2506.00131","title":"Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization","created":"2025-05-30","cited_by_count":1,"area":"offlinerl"}],"next_cursor":"100"}