{"total":18,"rows":[{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2305.16147","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","created":"2023-05-25","cited_by_count":19,"area":null},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2307.08873","title":"An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient","created":"2023-07-17","cited_by_count":12,"area":null},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2406.16782","title":"Confidence Aware Inverse Constrained Reinforcement Learning","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2406.19626","title":"Safety through feedback in Constrained RL","created":"2024-06-28","cited_by_count":5,"area":null},{"id":"2410.07525","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2206.11812","title":"Formalizing the Problem of Side Effect Regularization","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2407.12061","title":"Situated Instruction Following","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2202.10407","title":"Learning Behavioral Soft Constraints from Demonstrations","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2510.21560","title":"Learning Neural Control Barrier Functions from Expert Demonstrations using Inverse Constraint Learning","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2312.08837","title":"Learning Safety Constraints From Demonstration Using One-Class Decision Trees","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2408.01622","title":"Positive-Unlabeled Constraint Learning for Inferring Nonlinear Continuous Constraints Functions from Expert Demonstrations","created":"2024-08-03","cited_by_count":0,"area":null},{"id":"2602.20152","title":"Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2608.09222","title":"Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2610.02170","title":"Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}