{"total":100,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395,"area":"offlinerl"},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66,"area":"offlinerl"},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"area":null},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","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":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2405.20555","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning","created":"2024-05-31","cited_by_count":33,"area":"diffusion"},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2106.12764","title":"Density Constrained Reinforcement Learning","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2311.02013","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","created":"2023-11-03","cited_by_count":21,"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":"2411.19418","title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","created":"2024-11-29","cited_by_count":20,"area":"deeprl"},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2305.12944","title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs","created":"2023-05-22","cited_by_count":17,"area":"offlinerl"},{"id":"2402.08530","title":"A Distributional Analogue to the Successor Representation","created":"2024-02-13","cited_by_count":17,"area":"deeprl"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14,"area":"offlinerl"},{"id":"2402.12570","title":"Offline Multi-task Transfer RL with Representational Penalization","created":"2024-02-19","cited_by_count":14,"area":"offlinerl"},{"id":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12,"area":null},{"id":"2112.14004","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","created":"2021-12-28","cited_by_count":10,"area":"offlinerl"},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"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":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2311.02194","title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation","created":"2023-11-03","cited_by_count":10,"area":"offlinerl"},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10,"area":"offlinerl"},{"id":"2408.16286","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","created":"2024-08-29","cited_by_count":10,"area":"deeprl"},{"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":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"area":null},{"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":"2202.07071","title":"A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2304.10613","title":"Debiasing Conditional Stochastic Optimization","created":"2023-04-20","cited_by_count":6,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5,"area":null},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2407.12163","title":"Bellman Diffusion Models","created":"2024-07-16","cited_by_count":5,"area":"diffusion"},{"id":"2408.11084","title":"Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2409.05539","title":"CoBo: Collaborative Learning via Bilevel Optimization","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2504.16667","title":"Representation Learning via Non-Contrastive Mutual Information","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2109.11867","title":"The $f$-Divergence Reinforcement Learning Framework","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"},{"id":"2508.14383","title":"Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations","created":"2025-08-20","cited_by_count":3,"area":"offlinerl"},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2102.07889","title":"Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport","created":"2021-02-15","cited_by_count":1,"area":null},{"id":"2103.09756","title":"Near Optimal Policy Optimization via REPS","created":"2021-03-17","cited_by_count":1,"area":null},{"id":"2201.00236","title":"Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning","created":"2022-01-01","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2303.06654","title":"Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2404.16468","title":"A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints","created":"2024-04-25","cited_by_count":1,"area":"deeprl"},{"id":"2410.14665","title":"Online Reinforcement Learning with Passive Memory","created":"2024-10-18","cited_by_count":1,"area":"deeprl"},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.08644","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2507.10843","title":"Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps","created":"2025-07-14","cited_by_count":1,"area":"offlinerl"},{"id":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2509.19800","title":"Analysis of approximate linear programming solution to Markov decision problem with log barrier function","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2110.12081","title":"Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2203.16177","title":"Marginalized Operators for Off-policy Reinforcement Learning","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2209.13046","title":"Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective","created":"2022-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2210.00770","title":"Accelerate Reinforcement Learning with PID Controllers in the Pendulum Simulations","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2212.14405","title":"Offline Policy Optimization in RL with Variance Regularizaton","created":"2022-12-29","cited_by_count":0,"area":"offlinerl"},{"id":"2301.03183","title":"Minimax Weight Learning for Absorbing MDPs","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2309.16631","title":"Robust Offline Reinforcement Learning -- Certify the Confidence Interval","created":"2023-09-28","cited_by_count":0,"area":"offlinerl"},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"id":"2409.00418","title":"Robust off-policy Reinforcement Learning via Soft Constrained Adversary","created":"2024-08-31","cited_by_count":0,"area":"deeprl"},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.16753","title":"Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation","created":"2025-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2508.04225","title":"Symmetric Behavior Regularized Policy Optimization","created":"2025-08-06","cited_by_count":0,"area":"offlinerl"},{"id":"2509.15103","title":"Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2601.20154","title":"Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.03454","title":"[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2609.24489","title":"Lifted Bellman Linear Programming for Offline Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}