{"total":75,"rows":[{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239,"area":"lr"},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91,"area":"offlinerl"},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77,"area":"offlinerl"},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60,"area":"driving"},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"1905.11108","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","created":"2019-05-27","cited_by_count":28,"area":"offlinerl"},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"1803.05402","title":"Imitation Learning with Concurrent Actions in 3D Games","created":"2018-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"1905.12310","title":"Adversarial Imitation Learning from Incomplete Demonstrations","created":"2019-05-29","cited_by_count":16,"area":"offlinerl"},{"id":"2009.14509","title":"Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning","created":"2020-09-30","cited_by_count":14,"area":"offlinerl"},{"id":"2210.07432","title":"Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations","created":"2022-10-14","cited_by_count":14,"area":null},{"id":"1803.01129","title":"OIL: Observational Imitation Learning","created":"2018-03-03","cited_by_count":11,"area":"offlinerl"},{"id":"2402.01886","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","created":"2024-02-02","cited_by_count":11,"area":"offlinerl"},{"id":"2011.13467","title":"Episodic Self-Imitation Learning with Hindsight","created":"2020-11-26","cited_by_count":10,"area":"offlinerl"},{"id":"2104.08441","title":"Action Advising with Advice Imitation in Deep Reinforcement Learning","created":"2021-04-17","cited_by_count":10,"area":"distill"},{"id":"2110.01840","title":"Deep reinforcement learning for guidewire navigation in coronary artery phantom","created":"2021-10-05","cited_by_count":10,"area":null},{"id":"2211.07882","title":"Explainable Action Advising for Multi-Agent Reinforcement Learning","created":"2022-11-15","cited_by_count":10,"area":"distill"},{"id":"2407.15134","title":"Proximal Policy Distillation","created":"2024-07-21","cited_by_count":9,"area":"distill"},{"id":"1808.07903","title":"LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations","created":"2018-08-23","cited_by_count":8,"area":"offlinerl"},{"id":"2106.14866","title":"Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits","created":"2021-06-28","cited_by_count":8,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2209.10149","title":"Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation","created":"2022-09-21","cited_by_count":7,"area":"offlinerl"},{"id":"1907.03976","title":"Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations","created":"2019-07-09","cited_by_count":6,"area":"offlinerl"},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2405.00746","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","created":"2024-04-30","cited_by_count":6,"area":"deeprl"},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2101.05893","title":"Instance-Aware Predictive Navigation in Multi-Agent Environments","created":"2021-01-14","cited_by_count":5,"area":"driving"},{"id":"2110.05286","title":"Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning","created":"2021-10-11","cited_by_count":5,"area":null},{"id":"2110.14464","title":"Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabeling","created":"2021-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2212.01509","title":"Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2302.00808","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2209.09446","title":"A Joint Imitation-Reinforcement Learning Framework for Reduced Baseline Regret","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2212.06998","title":"Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning","created":"2022-12-14","cited_by_count":3,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2008.01913","title":"Generalization Guarantees for Imitation Learning","created":"2020-08-05","cited_by_count":2,"area":"offlinerl"},{"id":"2103.14823","title":"Co-Imitation Learning without Expert Demonstration","created":"2021-03-27","cited_by_count":2,"area":"offlinerl"},{"id":"2104.06600","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","created":"2021-04-14","cited_by_count":2,"area":"offlinerl"},{"id":"2104.12842","title":"End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning","created":"2021-04-26","cited_by_count":2,"area":null},{"id":"2412.03803","title":"Towards an Autonomous Test Driver: High-Performance Driver Modeling via Reinforcement Learning","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2503.23650","title":"A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective","created":"2025-03-31","cited_by_count":2,"area":"driving"},{"id":"2504.05585","title":"TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning","created":"2025-04-08","cited_by_count":2,"area":"offlinerl"},{"id":"2105.14639","title":"Shaped Policy Search for Evolutionary Strategies using Waypoints","created":"2021-05-30","cited_by_count":1,"area":null},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"area":"offlinerl"},{"id":"2501.07502","title":"Human-Inspired Multi-Level Reinforcement Learning","created":"2025-01-13","cited_by_count":1,"area":"deeprl"},{"id":"2509.04069","title":"Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning","created":"2025-09-04","cited_by_count":1,"area":"deeprl"},{"id":"2510.09096","title":"When a Robot is More Capable than a Human: Learning from Constrained Demonstrators","created":"2025-10-10","cited_by_count":1,"area":"offlinerl"},{"id":"2107.06840","title":"Mixing Human Demonstrations with Self-Exploration in Experience Replay for Deep Reinforcement Learning","created":"2021-07-14","cited_by_count":0,"area":null},{"id":"2110.04633","title":"Credit Assignment Safety Learning from Human Demonstrations","created":"2021-10-09","cited_by_count":0,"area":"offlinerl"},{"id":"2202.02395","title":"Malleable Agents for Re-Configurable Robotic Manipulators","created":"2022-02-04","cited_by_count":0,"area":null},{"id":"2202.11325","title":"Reinforcement Learning from Demonstrations by Novel Interactive Expert and Application to Automatic Berthing Control Systems for Unmanned Surface Vessel","created":"2022-02-23","cited_by_count":0,"area":"offlinerl"},{"id":"2205.11019","title":"Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies","created":"2022-05-23","cited_by_count":0,"area":"offlinerl"},{"id":"2207.00751","title":"Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity","created":"2022-07-02","cited_by_count":0,"area":null},{"id":"2208.00478","title":"Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination","created":"2022-07-31","cited_by_count":0,"area":"offlinerl"},{"id":"2212.10705","title":"Control of Continuous Quantum Systems with Many Degrees of Freedom based on Convergent Reinforcement Learning","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2301.11153","title":"Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2304.06055","title":"Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2402.18836","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","created":"2024-02-29","cited_by_count":0,"area":"deeprl"},{"id":"2408.05610","title":"Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations","created":"2024-08-10","cited_by_count":0,"area":"alignment"},{"id":"2504.04326","title":"Economic Battery Storage Dispatch with Deep Reinforcement Learning from Rule-Based Demonstrations","created":"2025-04-06","cited_by_count":0,"area":"deeprl"},{"id":"2505.15275","title":"Learning-based Autonomous Oversteer Control and Collision Avoidance","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2509.15981","title":"Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations","created":"2025-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2509.23778","title":"Sequence Pathfinder for Multi-Agent Pickup and Delivery in the Warehouse","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2605.30903","title":"Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"},{"id":"2609.03590","title":"From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control","created":"2026-09-03","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}