{"total":16,"rows":[{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2106.00600","title":"Fair Clustering Using Antidote Data","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2111.04698","title":"Interactive Inverse Reinforcement Learning for Cooperative Games","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2111.07083","title":"Learning Data Teaching Strategies Via Knowledge Tracing","created":"2021-11-13","cited_by_count":6,"area":null},{"id":"2309.02876","title":"Non-Clashing Teaching Maps for Balls in Graphs","created":"2023-09-06","cited_by_count":6,"area":null},{"id":"2503.07665","title":"The Computational Complexity of Positive Non-Clashing Teaching in Graphs","created":"2025-03-08","cited_by_count":3,"area":null},{"id":"2103.07815","title":"Dynamically Switching Human Prediction Models for Efficient Planning","created":"2021-03-13","cited_by_count":2,"area":null},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2309.17275","title":"Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2602.00657","title":"Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2103.13268","title":"Address Behaviour Vulnerabilities in the Next Generation of Autonomous Robots","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2204.12072","title":"Know Thy Student: Interactive Learning with Gaussian Processes","created":"2022-04-26","cited_by_count":0,"area":null},{"id":"2309.09095","title":"Interactively Teaching an Inverse Reinforcement Learner with Limited Feedback","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2311.15399","title":"Optimally Teaching a Linear Behavior Cloning Agent","created":"2023-11-26","cited_by_count":0,"area":null}],"next_cursor":null}