{"total":10,"rows":[{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2105.15119","title":"Policies for the Dynamic Traveling Maintainer Problem with Alerts","created":"2021-05-31","cited_by_count":1,"area":null},{"id":"2205.15824","title":"Graph Backup: Data Efficient Backup Exploiting Markovian Transitions","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2511.09792","title":"Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2204.03840","title":"Data-Driven Evaluation of Training Action Space for Reinforcement Learning","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2210.04820","title":"Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2307.09109","title":"Mining of Single-Class by Active Learning for Semantic Segmentation","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2607.19397","title":"Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning","created":"2026-07-04","cited_by_count":0,"area":null}],"next_cursor":null}