{"total":21,"rows":[{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25,"area":null},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2208.10483","title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2209.00532","title":"Actor Prioritized Experience Replay","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2104.11861","title":"Class-Incremental Experience Replay for Continual Learning under Concept Drift","created":"2021-04-24","cited_by_count":17,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17,"area":null},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2303.10227","title":"Conversational Tree Search: A New Hybrid Dialog Task","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2206.03171","title":"Introspective Experience Replay: Look Back When Surprised","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2105.08666","title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2303.16529","title":"Importance Sampling for Stochastic Gradient Descent in Deep Neural Networks","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2309.06684","title":"Attention Loss Adjusted Prioritized Experience Replay","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2311.14390","title":"Directly Attention Loss Adjusted Prioritized Experience Replay","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2310.08091","title":"Discerning Temporal Difference Learning","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2608.06015","title":"ProDVI: Programmatic Dynamics Priors for Value Network Initialization","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.25297","title":"Correcting Within-Group Self-Selection Bias in Prioritized Replay","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}