{"total":15,"rows":[{"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":"2109.13570","title":"Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing","created":"2021-09-28","cited_by_count":14,"area":null},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2110.00445","title":"Sim and Real: Better Together","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2112.04213","title":"Convergence Results For Q-Learning With Experience Replay","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2303.17655","title":"Q-Learning based system for path planning with unmanned aerial vehicles swarms in obstacle environments","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2102.11319","title":"Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning","created":"2021-02-22","cited_by_count":3,"area":null},{"id":"2205.09869","title":"Transformer with Memory Replay","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2306.04299","title":"Timing Process Interventions with Causal Inference and Reinforcement Learning","created":"2023-06-07","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":"2112.04229","title":"Replay For Safety","created":"2021-12-08","cited_by_count":0,"area":null},{"id":"2211.16687","title":"Automatic Discovery of Multi-perspective Process Model using Reinforcement Learning","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2607.06772","title":"Efficient Long-Horizon Learning for Learned Optimization","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}