{"total":40,"rows":[{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122,"area":null},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85,"area":null},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47,"area":null},{"id":"2111.07999","title":"Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization","created":"2021-11-15","cited_by_count":46,"area":null},{"id":"2103.12656","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","created":"2021-03-23","cited_by_count":38,"area":null},{"id":"2309.12300","title":"See to Touch: Learning Tactile Dexterity through Visual Incentives","created":"2023-09-21","cited_by_count":35,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2205.15023","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2107.01969","title":"The MineRL BASALT Competition on Learning from Human Feedback","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2205.05212","title":"A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning","created":"2022-05-11","cited_by_count":22,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2211.09019","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2201.08484","title":"Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming","created":"2022-01-20","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2209.00853","title":"TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification","created":"2022-09-02","cited_by_count":13,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2311.01388","title":"Time-series Generation by Contrastive Imitation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2308.09387","title":"Multi-Level Compositional Reasoning for Interactive Instruction Following","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2211.04786","title":"Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2102.12307","title":"Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2310.19831","title":"Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning","created":"2023-10-28","cited_by_count":3,"area":null},{"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":"2406.02450","title":"A Generalized Apprenticeship Learning Framework for Modeling Heterogeneous Student Pedagogical Strategies","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2406.05881","title":"Training Fast Robot Policies with Slow Foundation Models","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.09070","title":"An Offline Time-aware Apprenticeship Learning Framework for Evolving Reward Functions","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2505.17714","title":"PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2103.16629","title":"Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2301.07421","title":"DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2304.10260","title":"Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation","created":"2023-04-19","cited_by_count":0,"area":null},{"id":"2312.02352","title":"Working Backwards: Learning to Place by Picking","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2505.20110","title":"Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training","created":"2025-05-26","cited_by_count":0,"area":null}],"next_cursor":null}