{"total":20,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"1911.09676","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","created":"2019-11-21","cited_by_count":73,"area":"offlinerl"},{"id":"2212.05711","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","created":"2022-12-12","cited_by_count":71,"area":"offlinerl"},{"id":"1910.04854","title":"Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor","created":"2019-09-23","cited_by_count":44,"area":"offlinerl"},{"id":"1806.00047","title":"Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning","created":"2018-05-31","cited_by_count":27,"area":"offlinerl"},{"id":"2210.01841","title":"Learning Perception-Aware Agile Flight in Cluttered Environments","created":"2022-10-04","cited_by_count":23,"area":"offlinerl"},{"id":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18,"area":"offlinerl"},{"id":"2202.07600","title":"Bayesian Imitation Learning for End-to-End Mobile Manipulation","created":"2022-02-15","cited_by_count":14,"area":"offlinerl"},{"id":"2310.18247","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","created":"2023-10-27","cited_by_count":10,"area":"offlinerl"},{"id":"2202.01862","title":"Practical Imitation Learning in the Real World via Task Consistency Loss","created":"2022-02-03","cited_by_count":7,"area":"offlinerl"},{"id":"2008.12647","title":"ADAIL: Adaptive Adversarial Imitation Learning","created":"2020-08-23","cited_by_count":6,"area":"offlinerl"},{"id":"1907.06838","title":"Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving","created":"2019-07-16","cited_by_count":5,"area":"offlinerl"},{"id":"2202.02967","title":"Learning from Imperfect Demonstrations via Adversarial Confidence Transfer","created":"2022-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2311.14153","title":"Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFs","created":"2023-11-23","cited_by_count":1,"area":"offlinerl"},{"id":"2402.13201","title":"Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers","created":"2024-02-20","cited_by_count":1,"area":"offlinerl"},{"id":"2603.07578","title":"Approximate Imitation Learning for Event-based Quadrotor Flight in Cluttered Environments","created":"2026-03-08","cited_by_count":1,"area":"offlinerl"},{"id":"2205.09550","title":"Data Valuation for Offline Reinforcement Learning","created":"2022-05-19","cited_by_count":0,"area":"offlinerl"},{"id":"2605.01232","title":"A Principled Approach for Creating High-fidelity Synthetic Demonstrations for Imitation Learning","created":"2026-05-02","cited_by_count":0,"area":"offlinerl"},{"id":"2605.09183","title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","created":"2026-05-09","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}