{"total":90,"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":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"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":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27,"area":"offlinerl"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2206.01474","title":"Offline Reinforcement Learning with Causal Structured World Models","created":"2022-06-03","cited_by_count":19,"area":"wm"},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17,"area":null},{"id":"2411.09891","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","created":"2024-11-15","cited_by_count":17,"area":"offlinerl"},{"id":"2205.05569","title":"Delayed Reinforcement Learning by Imitation","created":"2022-05-11","cited_by_count":16,"area":null},{"id":"2306.06563","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","created":"2023-06-11","cited_by_count":16,"area":"offlinerl"},{"id":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","cited_by_count":15,"area":"offlinerl"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"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":"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":"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":"2306.14799","title":"On Imitation in Mean-field Games","created":"2023-06-26","cited_by_count":10,"area":"offlinerl"},{"id":"2405.15384","title":"Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate","created":"2024-05-24","cited_by_count":10,"area":"deeprl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","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":"2311.01388","title":"Time-series Generation by Contrastive Imitation","created":"2023-11-02","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":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9,"area":"offlinerl"},{"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":"2211.03408","title":"RITA: Boost Driving Simulators with Realistic Interactive Traffic Flow","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2305.03360","title":"A Survey on Offline Model-Based Reinforcement Learning","created":"2023-05-05","cited_by_count":7,"area":"offlinerl"},{"id":"2306.07106","title":"Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning","created":"2023-06-12","cited_by_count":7,"area":null},{"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":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2209.05530","title":"Model-based Reinforcement Learning with Multi-step Plan Value Estimation","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2212.03922","title":"Tight Performance Guarantees of Imitator Policies with Continuous Actions","created":"2022-12-07","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":"2206.00238","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","created":"2022-06-01","cited_by_count":5,"area":"offlinerl"},{"id":"2209.12868","title":"On Efficient Online Imitation Learning via Classification","created":"2022-09-26","cited_by_count":5,"area":"offlinerl"},{"id":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2106.09256","title":"Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning","created":"2021-06-17","cited_by_count":4,"area":"offlinerl"},{"id":"2312.11214","title":"Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective","created":"2023-12-18","cited_by_count":4,"area":"offlinerl"},{"id":"2502.02869","title":"Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds","created":"2025-02-05","cited_by_count":4,"area":"deeprl"},{"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":"2206.02000","title":"Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning","created":"2022-06-04","cited_by_count":3,"area":"offlinerl"},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2310.07143","title":"Imitation Learning from Purified Demonstrations","created":"2023-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","cited_by_count":3,"area":"alignment"},{"id":"2203.01696","title":"Fail-Safe Adversarial Generative Imitation Learning","created":"2022-03-03","cited_by_count":2,"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":"2303.07046","title":"Deploying Offline Reinforcement Learning with Human Feedback","created":"2023-03-13","cited_by_count":2,"area":"alignment"},{"id":"2404.18896","title":"Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models","created":"2024-04-29","cited_by_count":2,"area":"wm"},{"id":"2405.16668","title":"Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees","created":"2024-05-26","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":"2410.22728","title":"Offline Behavior Distillation","created":"2024-10-30","cited_by_count":2,"area":"deeprl"},{"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":"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":"2304.02480","title":"Quantum Imitation Learning","created":"2023-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2305.03987","title":"Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization","created":"2023-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2311.01589","title":"A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning","created":"2023-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2402.05525","title":"Differentially Private Deep Model-Based Reinforcement Learning","created":"2024-02-08","cited_by_count":1,"area":"offlinerl"},{"id":"2403.15079","title":"Automated Feature Selection for Inverse Reinforcement Learning","created":"2024-03-22","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":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2511.14396","title":"Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning","created":"2025-11-18","cited_by_count":1,"area":"vla"},{"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":"2206.00316","title":"Model Generation with Provable Coverability for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":0,"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":"2401.09728","title":"Offline Imitation Learning by Controlling the Effective Planning Horizon","created":"2024-01-18","cited_by_count":0,"area":"offlinerl"},{"id":"2401.11396","title":"Visual Imitation Learning with Calibrated Contrastive Representation","created":"2024-01-21","cited_by_count":0,"area":"offlinerl"},{"id":"2406.11562","title":"An Imitative Reinforcement Learning Framework for Pursuit-Lock-Launch Missions","created":"2024-06-17","cited_by_count":0,"area":"deeprl"},{"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":"2501.12785","title":"On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration","created":"2025-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2503.06893","title":"Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning","created":"2025-03-10","cited_by_count":0,"area":"offlinerl"},{"id":"2503.14833","title":"Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability","created":"2025-03-19","cited_by_count":0,"area":"diffusion"},{"id":"2505.20110","title":"Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2602.23737","title":"Bridging Dynamics Gaps via Diffusion Schr\\\"odinger Bridge for Cross-Domain Reinforcement Learning","created":"2026-02-27","cited_by_count":0,"area":"deeprl"},{"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":"2606.22056","title":"Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning","created":"2026-06-20","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}