{"total":13,"rows":[{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10,"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":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","cited_by_count":6,"area":null},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2203.07171","title":"Orchestrated Value Mapping for Reinforcement Learning","created":"2022-03-14","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":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2303.12785","title":"Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality","created":"2023-03-22","cited_by_count":2,"area":null},{"id":"2203.11677","title":"Robust Action Gap Increasing with Clipped Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2404.15518","title":"An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models","created":"2024-04-23","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}],"next_cursor":null}