{"total":35,"rows":[{"id":"2502.13900","title":"Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning","created":"2025-02-19","cited_by_count":12,"area":"offlinerl"},{"id":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2510.06499","title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","created":"2025-10-07","cited_by_count":8,"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":"2502.19859","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":"2509.21172","title":"Inverse Reinforcement Learning with Just Classification and a Few Regressions","created":"2025-09-25","cited_by_count":5,"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":"2601.21718","title":"When Does Predictive Inverse Dynamics Outperform Behavior Cloning?","created":"2026-01-29","cited_by_count":3,"area":"offlinerl"},{"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":"2412.07057","title":"Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning","created":"2024-12-09","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":"2504.13413","title":"A Model-Based Approach to Imitation Learning through Multi-Step Predictions","created":"2025-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2507.06404","title":"Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction","created":"2025-07-08","cited_by_count":1,"area":"offlinerl"},{"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":"2602.22810","title":"Multi-agent imitation learning with function approximation: Linear Markov games and beyond","created":"2026-02-26","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":"2605.14599","title":"Fast Rates for Inverse Reinforcement Learning","created":"2026-05-14","cited_by_count":1,"area":"offlinerl"},{"id":"2411.04056","title":"Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning","created":"2024-11-06","cited_by_count":0,"area":"offlinerl"},{"id":"2507.19535","title":"Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control Networks","created":"2025-07-22","cited_by_count":0,"area":"offlinerl"},{"id":"2510.16462","title":"Buzz, Choose, Forget: A Meta-Bandit Framework for Bee-Like Decision Making","created":"2025-10-18","cited_by_count":0,"area":"offlinerl"},{"id":"2602.21020","title":"Matching Multiple Experts: On the Exploitability of Multi-Agent Imitation Learning","created":"2026-02-24","cited_by_count":0,"area":"offlinerl"},{"id":"2602.21684","title":"Primary-Fine Decoupling for Action Generation in Robotic Imitation","created":"2026-02-25","cited_by_count":0,"area":"offlinerl"},{"id":"2603.08506","title":"Oracle-Guided Soft Shielding for Safe Move Prediction in Chess","created":"2026-03-09","cited_by_count":0,"area":"offlinerl"},{"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":"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":"2608.10473","title":"Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning","created":"2026-08-11","cited_by_count":0,"area":"offlinerl"},{"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"},{"id":"2609.38407","title":"Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies","created":"2026-09-29","cited_by_count":0,"area":"offlinerl"},{"id":"2610.01626","title":"Measuring the Stability Assumption Behind Action Chunking","created":"2026-10-01","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}