{"total":96,"rows":[{"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":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160,"area":"diffusion"},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85,"area":"offlinerl"},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83,"area":"offlinerl"},{"id":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81,"area":"offlinerl"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27,"area":"offlinerl"},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2205.15397","title":"Minimax Optimal Online Imitation Learning via Replay Estimation","created":"2022-05-30","cited_by_count":25,"area":"offlinerl"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"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":"2402.10450","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","created":"2024-02-16","cited_by_count":21,"area":"offlinerl"},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2306.06563","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","created":"2023-06-11","cited_by_count":16,"area":"offlinerl"},{"id":"2410.23916","title":"Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2412.04759","title":"REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments","created":"2024-12-06","cited_by_count":16,"area":"rag"},{"id":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","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":"2405.02181","title":"Imitation Learning in Discounted Linear MDPs without exploration assumptions","created":"2024-05-03","cited_by_count":15,"area":"offlinerl"},{"id":"2310.06171","title":"Memory-Consistent Neural Networks for Imitation Learning","created":"2023-10-09","cited_by_count":14,"area":"offlinerl"},{"id":"2602.21531","title":"LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies","created":"2026-02-25","cited_by_count":14,"area":null},{"id":"2603.21383","title":"PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost","created":"2026-03-22","cited_by_count":14,"area":"agents"},{"id":"2208.01899","title":"Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis","created":"2022-08-03","cited_by_count":13,"area":"offlinerl"},{"id":"2102.12948","title":"Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally","created":"2021-02-25","cited_by_count":12,"area":"offlinerl"},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12,"area":null},{"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":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2108.08765","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","created":"2021-08-19","cited_by_count":11,"area":"offlinerl"},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2303.01094","title":"CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2303.02073","title":"How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement","created":"2023-03-03","cited_by_count":8,"area":"offlinerl"},{"id":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2510.15464","title":"Learning to Answer from Correct Demonstrations","created":"2025-10-17","cited_by_count":7,"area":null},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2502.08259","title":"Balancing optimism and pessimism in offline-to-online learning","created":"2025-02-12","cited_by_count":6,"area":"offlinerl"},{"id":"2209.12868","title":"On Efficient Online Imitation Learning via Classification","created":"2022-09-26","cited_by_count":5,"area":"offlinerl"},{"id":"2306.08232","title":"Curricular Subgoals for Inverse Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2403.09701","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2406.03812","title":"How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach","created":"2024-06-06","cited_by_count":5,"area":"offlinerl"},{"id":"2408.05885","title":"GFlowNet Training by Policy Gradients","created":"2024-08-12","cited_by_count":5,"area":"deeprl"},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","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":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2312.00054","title":"Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective","created":"2023-11-29","cited_by_count":4,"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":"2505.17610","title":"Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning","created":"2025-05-23","cited_by_count":4,"area":"offlinerl"},{"id":"2603.20607","title":"Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models","created":"2026-03-21","cited_by_count":4,"area":"wm"},{"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":"2402.16349","title":"C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory","created":"2024-02-26","cited_by_count":3,"area":"offlinerl"},{"id":"2403.19462","title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","created":"2024-03-28","cited_by_count":3,"area":"offlinerl"},{"id":"2510.03207","title":"To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning","created":"2025-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2511.13765","title":"PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning","created":"2025-11-14","cited_by_count":3,"area":"alignment"},{"id":"2604.23000","title":"Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning","created":"2026-04-24","cited_by_count":3,"area":"offlinerl"},{"id":"2606.30445","title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","created":"2026-06-29","cited_by_count":3,"area":"offlinerl"},{"id":"2301.11687","title":"Theoretical Analysis of Offline Imitation With Supplementary Dataset","created":"2023-01-27","cited_by_count":2,"area":"offlinerl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2411.18201","title":"Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2412.07057","title":"Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning","created":"2024-12-09","cited_by_count":2,"area":"offlinerl"},{"id":"2503.23270","title":"Localized Graph-Based Neural Dynamics Models for Terrain Manipulation","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2508.21501","title":"Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting","created":"2025-08-29","cited_by_count":2,"area":"offlinerl"},{"id":"2510.09325","title":"Rate optimal learning of equilibria from data","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2510.09487","title":"Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2606.26006","title":"FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation","created":"2026-06-24","cited_by_count":2,"area":"vla"},{"id":"2304.02480","title":"Quantum Imitation Learning","created":"2023-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2402.16247","title":"Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2503.17865","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","created":"2025-03-22","cited_by_count":1,"area":"offlinerl"},{"id":"2503.22524","title":"Robust Offline Imitation Learning Through State-level Trajectory Stitching","created":"2025-03-28","cited_by_count":1,"area":"offlinerl"},{"id":"2506.20307","title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","created":"2025-06-25","cited_by_count":1,"area":"offlinerl"},{"id":"2507.21452","title":"Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training","created":"2025-07-29","cited_by_count":1,"area":"diffusion"},{"id":"2510.15786","title":"DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2510.24095","title":"Learning Parameterized Skills from Demonstrations","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2605.01778","title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2206.05521","title":"Model-based Offline Imitation Learning with Non-expert Data","created":"2022-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2407.00419","title":"On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2408.11822","title":"State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Survey","created":"2024-08-03","cited_by_count":0,"area":null},{"id":"2506.01624","title":"Social Cooperation in Conversational AI Agents","created":"2025-06-02","cited_by_count":0,"area":"agents"},{"id":"2603.20538","title":"Understanding Behavior Cloning with Action Quantization","created":"2026-03-20","cited_by_count":0,"area":"offlinerl"},{"id":"2603.22713","title":"Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism","created":"2026-03-24","cited_by_count":0,"area":"offlinerl"},{"id":"2604.03759","title":"Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation","created":"2026-04-04","cited_by_count":0,"area":"offlinerl"},{"id":"2605.05081","title":"Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations","created":"2026-05-06","cited_by_count":0,"area":"offlinerl"},{"id":"2605.12000","title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","created":"2026-05-12","cited_by_count":0,"area":"offlinerl"},{"id":"2606.22056","title":"Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning","created":"2026-06-20","cited_by_count":0,"area":"offlinerl"},{"id":"2607.06772","title":"Efficient Long-Horizon Learning for Learned Optimization","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.11660","title":"Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing","created":"2026-08-12","cited_by_count":0,"area":"distill"},{"id":"2609.19669","title":"Beyond Patch Removal: Persistent Adversarial Effects in Vision-Language-Action Policies","created":"2026-09-17","cited_by_count":0,"area":"vla"},{"id":"2609.33291","title":"The Statistical Benefits of Multiple Responses for Learning from Demonstrations","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35698","title":"Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}