{"total":25,"rows":[{"id":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45,"area":null},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2209.10187","title":"On the convex formulations of robust Markov decision processes","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2209.13413","title":"Reinforcement Learning with Non-Exponential Discounting","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2312.10385","title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","created":"2023-12-16","cited_by_count":7,"area":null},{"id":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2402.14174","title":"Blending Data-Driven Priors in Dynamic Games","created":"2024-02-21","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":"2406.19626","title":"Safety through feedback in Constrained RL","created":"2024-06-28","cited_by_count":5,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2207.01955","title":"Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2303.16698","title":"Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2305.14859","title":"Utility-Probability Duality of Neural Networks","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2407.09809","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2407.11658","title":"Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2409.13299","title":"OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2506.15190","title":"Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2312.04786","title":"Joint User Association, Interference Cancellation and Power Control for Multi-IRS Assisted UAV Communications","created":"2023-12-08","cited_by_count":0,"area":null},{"id":"2405.15975","title":"Inference of Utilities and Time Preference in Sequential Decision-Making","created":"2024-05-24","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},{"id":"2609.07303","title":"Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}