{"total":19,"rows":[{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2108.12121","title":"Reinforcement Learning-powered Semantic Communication via Semantic Similarity","created":"2021-08-27","cited_by_count":15,"area":null},{"id":"2206.05291","title":"ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2209.10341","title":"LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2206.13637","title":"Utility Theory for Sequential Decision Making","created":"2022-06-27","cited_by_count":8,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2302.03608","title":"Online Reinforcement Learning with Uncertain Episode Lengths","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2304.05073","title":"A Tale of Sampling and Estimation in Discounted Reinforcement Learning","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2307.12184","title":"On the Expressivity of Multidimensional Markov Reward","created":"2023-07-22","cited_by_count":4,"area":null},{"id":"2302.05740","title":"UGAE: A Novel Approach to Non-exponential Discounting","created":"2023-02-11","cited_by_count":3,"area":null},{"id":"2306.11208","title":"The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2110.13373","title":"EnTRPO: Trust Region Policy Optimization Method with Entropy Regularization","created":"2021-10-26","cited_by_count":2,"area":null},{"id":"2505.12049","title":"Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2105.02580","title":"Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2307.10305","title":"Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2210.05262","title":"Factors of Influence of the Overestimation Bias of Q-Learning","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2307.10491","title":"Markov Decision Processes with Time-Varying Geometric Discounting","created":"2023-07-19","cited_by_count":0,"area":null}],"next_cursor":null}