{"total":26,"rows":[{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"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":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"2210.04443","title":"Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2311.03485","title":"CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations","created":"2023-11-06","cited_by_count":9,"area":null},{"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":"2210.04303","title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","created":"2022-10-09","cited_by_count":5,"area":null},{"id":"2306.11168","title":"Learning Models of Adversarial Agent Behavior under Partial Observability","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5,"area":null},{"id":"2107.04533","title":"Behavior Self-Organization Supports Task Inference for Continual Robot Learning","created":"2021-07-09","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2212.01343","title":"CT-DQN: Control-Tutored Deep Reinforcement Learning","created":"2022-12-02","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":"2312.05044","title":"Backward Learning for Goal-Conditioned Policies","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2112.15221","title":"Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning","created":"2021-12-30","cited_by_count":1,"area":null},{"id":"2101.01366","title":"A Symmetric Loss Perspective of Reliable Machine Learning","created":"2021-01-05","cited_by_count":0,"area":null},{"id":"2111.14294","title":"Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2305.15193","title":"Adaptive Policy Learning to Additional Tasks","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2601.19411","title":"Task-Centric Policy Optimization from Misaligned Motion Priors","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2604.00258","title":"Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.12200","title":"Implicit Neural Representations of Individual Behavior","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.36924","title":"Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}