{"total":99,"rows":[{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"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":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154,"area":"offlinerl"},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133,"area":"offlinerl"},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107,"area":"offlinerl"},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63,"area":"offlinerl"},{"id":"2206.13414","title":"Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning","created":"2022-06-27","cited_by_count":61,"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":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2310.17086","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","created":"2023-10-26","cited_by_count":49,"area":"offlinerl"},{"id":"2110.14754","title":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality","created":"2021-10-27","cited_by_count":44,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2411.12633","title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","created":"2024-11-19","cited_by_count":39,"area":"offlinerl"},{"id":"2306.06569","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","created":"2023-06-11","cited_by_count":34,"area":"offlinerl"},{"id":"2204.10759","title":"The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models","created":"2022-04-22","cited_by_count":31,"area":"offlinerl"},{"id":"2111.01365","title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","created":"2021-11-02","cited_by_count":27,"area":"offlinerl"},{"id":"2111.04714","title":"A Dataset Perspective on Offline Reinforcement Learning","created":"2021-11-08","cited_by_count":27,"area":"offlinerl"},{"id":"2205.14850","title":"Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning","created":"2022-05-30","cited_by_count":22,"area":"offlinerl"},{"id":"2112.15579","title":"Single-Shot Pruning for Offline Reinforcement Learning","created":"2021-12-31","cited_by_count":21,"area":"offlinerl"},{"id":"2210.09598","title":"Planning for Sample Efficient Imitation Learning","created":"2022-10-18","cited_by_count":20,"area":"offlinerl"},{"id":"2306.14079","title":"Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching","created":"2023-06-24","cited_by_count":17,"area":"offlinerl"},{"id":"2406.16087","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","created":"2024-06-23","cited_by_count":16,"area":"offlinerl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","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":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13,"area":"offlinerl"},{"id":"2405.19909","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","created":"2024-05-30","cited_by_count":13,"area":"offlinerl"},{"id":"2403.07262","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","created":"2024-03-12","cited_by_count":11,"area":"offlinerl"},{"id":"2201.06539","title":"Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learning","created":"2022-01-17","cited_by_count":10,"area":"offlinerl"},{"id":"2301.00051","title":"Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks","created":"2022-12-30","cited_by_count":10,"area":"offlinerl"},{"id":"2302.12604","title":"Neural Laplace Control for Continuous-time Delayed Systems","created":"2023-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2402.03647","title":"CAMBranch: Contrastive Learning with Augmented MILPs for Branching","created":"2024-02-06","cited_by_count":10,"area":"offlinerl"},{"id":"2107.05007","title":"Generating stable molecules using imitation and reinforcement learning","created":"2021-07-11","cited_by_count":9,"area":"offlinerl"},{"id":"2108.01867","title":"A Pragmatic Look at Deep Imitation Learning","created":"2021-08-04","cited_by_count":9,"area":"offlinerl"},{"id":"2311.04726","title":"Social Motion Prediction with Cognitive Hierarchies","created":"2023-11-08","cited_by_count":9,"area":"offlinerl"},{"id":"2410.14069","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","created":"2024-10-17","cited_by_count":9,"area":"offlinerl"},{"id":"2201.11981","title":"Transfering Hierarchical Structure with Dual Meta Imitation Learning","created":"2022-01-28","cited_by_count":7,"area":"offlinerl"},{"id":"2211.09817","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","created":"2022-11-17","cited_by_count":7,"area":"offlinerl"},{"id":"2402.02017","title":"Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning","created":"2024-02-03","cited_by_count":7,"area":"offlinerl"},{"id":"2002.10525","title":"Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic","created":"2020-02-24","cited_by_count":6,"area":"offlinerl"},{"id":"2112.00950","title":"Quantile Filtered Imitation Learning","created":"2021-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2210.08121","title":"Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors","created":"2022-10-17","cited_by_count":6,"area":"offlinerl"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2202.04675","title":"Bayesian Nonparametrics for Offline Skill Discovery","created":"2022-02-09","cited_by_count":5,"area":"offlinerl"},{"id":"2211.02667","title":"Deconfounding Imitation Learning with Variational Inference","created":"2022-11-04","cited_by_count":5,"area":"offlinerl"},{"id":"2412.07544","title":"Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery","created":"2024-12-10","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19946","title":"Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^\\pi$-Realizable MDPs","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2208.05327","title":"Fast Offline Policy Optimization for Large Scale Recommendation","created":"2022-08-08","cited_by_count":4,"area":"offlinerl"},{"id":"2302.02607","title":"Target-based Surrogates for Stochastic Optimization","created":"2023-02-06","cited_by_count":4,"area":"offlinerl"},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2103.02863","title":"Inverse Reinforcement Learning with Explicit Policy Estimates","created":"2021-03-04","cited_by_count":3,"area":"offlinerl"},{"id":"2112.08932","title":"Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning","created":"2021-12-16","cited_by_count":3,"area":"offlinerl"},{"id":"2206.02095","title":"ARC - Actor Residual Critic for Adversarial Imitation Learning","created":"2022-06-05","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":"2402.07344","title":"Measurement Scheduling for ICU Patients with Offline Reinforcement Learning","created":"2024-02-12","cited_by_count":3,"area":"offlinerl"},{"id":"2403.00550","title":"Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking","created":"2024-03-01","cited_by_count":3,"area":"offlinerl"},{"id":"2509.22023","title":"Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error","created":"2025-09-26","cited_by_count":3,"area":"offlinerl"},{"id":"2603.08118","title":"Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting","created":"2026-03-09","cited_by_count":3,"area":"offlinerl"},{"id":"2103.14823","title":"Co-Imitation Learning without Expert Demonstration","created":"2021-03-27","cited_by_count":2,"area":"offlinerl"},{"id":"2108.00625","title":"Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning","created":"2021-08-02","cited_by_count":2,"area":"offlinerl"},{"id":"2301.09770","title":"Language-guided Task Adaptation for Imitation Learning","created":"2023-01-24","cited_by_count":2,"area":"offlinerl"},{"id":"2302.14833","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":2,"area":"offlinerl"},{"id":"2412.14834","title":"Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning","created":"2024-12-19","cited_by_count":2,"area":"offlinerl"},{"id":"2502.04979","title":"Prompt Tuning Decision Transformers with Structured and Scalable Bandits","created":"2025-02-07","cited_by_count":2,"area":"offlinerl"},{"id":"2503.03056","title":"A2Perf: Real-World Autonomous Agents Benchmark","created":"2025-03-04","cited_by_count":2,"area":"offlinerl"},{"id":"2506.17155","title":"Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity","created":"2025-06-20","cited_by_count":2,"area":"offlinerl"},{"id":"2602.04213","title":"InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersons","created":"2026-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2602.06603","title":"The hidden risks of temporal resampling in clinical reinforcement learning","created":"2026-02-06","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":"2212.02620","title":"Benchmarking Offline Reinforcement Learning Algorithms for E-Commerce Order Fraud Evaluation","created":"2022-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2312.03177","title":"Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning","created":"2023-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2404.03386","title":"SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring","created":"2024-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2511.12075","title":"Treatment Stitching with Schr\\\"odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies","created":"2025-11-15","cited_by_count":1,"area":"offlinerl"},{"id":"2608.17323","title":"ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback","created":"2026-08-18","cited_by_count":1,"area":"offlinerl"},{"id":"2103.05895","title":"WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata","created":"2021-03-10","cited_by_count":0,"area":"offlinerl"},{"id":"2106.06762","title":"Solving Graph-based Public Good Games with Tree Search and Imitation Learning","created":"2021-06-12","cited_by_count":0,"area":"offlinerl"},{"id":"2303.07846","title":"Sample-efficient Adversarial Imitation Learning","created":"2023-03-14","cited_by_count":0,"area":"offlinerl"},{"id":"2309.06658","title":"Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data Sets","created":"2023-09-13","cited_by_count":0,"area":"offlinerl"},{"id":"2312.12191","title":"CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning","created":"2023-12-19","cited_by_count":0,"area":"offlinerl"},{"id":"2406.03735","title":"Phase-Amplitude Reduction-Based Imitation Learning","created":"2024-06-06","cited_by_count":0,"area":"offlinerl"},{"id":"2501.03676","title":"SALE-Based Offline Reinforcement Learning with Ensemble Q-Networks","created":"2025-01-07","cited_by_count":0,"area":"offlinerl"},{"id":"2508.11767","title":"Limitation Learning: Catching Adverse Dialog with GAIL","created":"2025-08-15","cited_by_count":0,"area":"offlinerl"},{"id":"2509.26294","title":"Noise-Guided Transport for Imitation Learning","created":"2025-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2512.14726","title":"Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2603.02935","title":"Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2603.28008","title":"Energy-Aware Imitation Learning for Steering Prediction Using Events and Frames","created":"2026-03-30","cited_by_count":0,"area":"offlinerl"},{"id":"2604.02438","title":"Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models","created":"2026-04-02","cited_by_count":0,"area":"offlinerl"},{"id":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.00623","title":"Recovering Hidden Reward in Diffusion-Based Policies","created":"2026-05-01","cited_by_count":0,"area":"offlinerl"},{"id":"2605.24862","title":"Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets","created":"2026-05-24","cited_by_count":0,"area":"offlinerl"},{"id":"2610.01652","title":"Iterative Policy Refinement through Semantic Rollout Analysis","created":"2026-10-01","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}