{"total":121,"rows":[{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"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":"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":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"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":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","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":"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":"2110.09796","title":"Offline Reinforcement Learning with Value-based Episodic Memory","created":"2021-10-19","cited_by_count":36,"area":"offlinerl"},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"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":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2303.02569","title":"Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching","created":"2023-03-05","cited_by_count":24,"area":"offlinerl"},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"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":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"area":null},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"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":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","cited_by_count":15,"area":"offlinerl"},{"id":"2212.13861","title":"Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints","created":"2022-12-28","cited_by_count":15,"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":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"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":"2505.10881","title":"Prior-Guided Diffusion Planning for Offline Reinforcement Learning","created":"2025-05-16","cited_by_count":14,"area":"diffusion"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","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":"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":"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":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10,"area":"deeprl"},{"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":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2412.15429","title":"Offline Safe Reinforcement Learning Using Trajectory Classification","created":"2024-12-19","cited_by_count":9,"area":"offlinerl"},{"id":"2602.13810","title":"Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation","created":"2026-02-14","cited_by_count":9,"area":"deeprl"},{"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":"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":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2312.10802","title":"GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation","created":"2023-12-17","cited_by_count":6,"area":"offlinerl"},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2302.03770","title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","created":"2023-02-07","cited_by_count":5,"area":"offlinerl"},{"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":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"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":"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":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"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":"2405.12421","title":"A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback","created":"2024-05-20","cited_by_count":4,"area":"alignment"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2309.14989","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2311.01329","title":"A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2405.03892","title":"Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flows","created":"2024-05-06","cited_by_count":2,"area":"offlinerl"},{"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":"2602.01962","title":"Zero-Shot Off-Policy Learning","created":"2026-02-02","cited_by_count":2,"area":null},{"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":"2305.12679","title":"Offline Reinforcement Learning with Additional Covering Distributions","created":"2023-05-22","cited_by_count":1,"area":"offlinerl"},{"id":"2309.16188","title":"Stackelberg Batch Policy Learning","created":"2023-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2311.14885","title":"Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning","created":"2023-11-25","cited_by_count":1,"area":"offlinerl"},{"id":"2407.13006","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2410.17898","title":"Scalable Offline Reinforcement Learning for Mean Field Games","created":"2024-10-23","cited_by_count":1,"area":"offlinerl"},{"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":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"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":"2511.05844","title":"Enhancing Diffusion Model Guidance through Calibration and Regularization","created":"2025-11-08","cited_by_count":1,"area":"diffusion"},{"id":"2511.23442","title":"ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts","created":"2025-11-28","cited_by_count":1,"area":"offlinerl"},{"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":"2602.21072","title":"Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning","created":"2026-02-24","cited_by_count":1,"area":"offlinerl"},{"id":"2603.22292","title":"Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning","created":"2026-03-08","cited_by_count":1,"area":"offlinerl"},{"id":"2603.22430","title":"Inference Time Policy Optimization for Offline RL with Differentiable World Models","created":"2026-03-23","cited_by_count":1,"area":"wm"},{"id":"2609.06882","title":"Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning","created":"2026-09-07","cited_by_count":1,"area":"diffusion"},{"id":"2209.13132","title":"DCE: Offline Reinforcement Learning With Double Conservative Estimates","created":"2022-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2211.15065","title":"State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning","created":"2022-11-28","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":"2401.09728","title":"Offline Imitation Learning by Controlling the Effective Planning Horizon","created":"2024-01-18","cited_by_count":0,"area":"offlinerl"},{"id":"2408.15368","title":"Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning","created":"2024-08-27","cited_by_count":0,"area":"offlinerl"},{"id":"2502.00850","title":"Dual Alignment Maximin Optimization for Offline Model-based RL","created":"2025-02-02","cited_by_count":0,"area":"offlinerl"},{"id":"2505.21182","title":"Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations","created":"2025-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2506.02577","title":"Reachability Weighted Offline Goal-conditioned Resampling","created":"2025-06-03","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}