{"total":13,"rows":[{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70,"area":"offlinerl"},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27,"area":"offlinerl"},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2310.18434","title":"Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage","created":"2023-10-27","cited_by_count":12,"area":"offlinerl"},{"id":"2103.12945","title":"On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions","created":"2021-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2109.10854","title":"Imitation Learning of Stabilizing Policies for Nonlinear Systems","created":"2021-09-22","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":"2306.10071","title":"Joint Path planning and Power Allocation of a Cellular-Connected UAV using Apprenticeship Learning via Deep Inverse Reinforcement Learning","created":"2023-06-15","cited_by_count":2,"area":"offlinerl"},{"id":"2007.02520","title":"Explaining Fast Improvement in Online Imitation Learning","created":"2020-07-06","cited_by_count":1,"area":"offlinerl"},{"id":"2203.05774","title":"Reinforcement Learning for Linear Quadratic Control is Vulnerable Under Cost Manipulation","created":"2022-03-11","cited_by_count":1,"area":"offlinerl"},{"id":"2501.15957","title":"Inverse Reinforcement Learning via Convex Optimization","created":"2025-01-27","cited_by_count":0,"area":"offlinerl"},{"id":"2603.03454","title":"[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}