{"total":25,"rows":[{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2502.00472","title":"Binned Spectral Power Loss for Improved Prediction of Chaotic Systems","created":"2025-02-01","cited_by_count":10,"area":null},{"id":"2210.09960","title":"Rethinking Value Function Learning for Generalization in Reinforcement Learning","created":"2022-10-18","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":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2111.00206","title":"One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2204.12937","title":"Learning to Transfer Role Assignment Across Team Sizes","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","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":"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":"2511.17581","title":"EgoCogNav: Cognition-aware Human Egocentric Navigation","created":"2025-11-15","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":"2206.14267","title":"Applications of Reinforcement Learning in Finance -- Trading with a Double Deep Q-Network","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2503.11586","title":"Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2108.02323","title":"Active Reinforcement Learning over MDPs","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2211.10550","title":"Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function","created":"2022-11-19","cited_by_count":0,"area":null},{"id":"2212.14530","title":"POMRL: No-Regret Learning-to-Plan with Increasing Horizons","created":"2022-12-30","cited_by_count":0,"area":null},{"id":"2507.12989","title":"A Translation of Probabilistic Event Calculus into Markov Decision Processes","created":"2025-07-17","cited_by_count":0,"area":null}],"next_cursor":null}