{"total":18,"rows":[{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92,"area":null},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"area":null},{"id":"2312.02828","title":"Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications","created":"2023-12-05","cited_by_count":15,"area":null},{"id":"2110.15843","title":"Adaptive Discretization in Online Reinforcement Learning","created":"2021-10-29","cited_by_count":12,"area":null},{"id":"2110.04422","title":"Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation","created":"2021-10-09","cited_by_count":11,"area":null},{"id":"2111.06781","title":"Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity","created":"2021-11-12","cited_by_count":11,"area":null},{"id":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2110.12276","title":"Coarse-Grained Smoothness for RL in Metric Spaces","created":"2021-10-23","cited_by_count":2,"area":null},{"id":"2406.09375","title":"Learning conditional distributions on continuous spaces","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2109.02786","title":"Deep SIMBAD: Active Landmark-based Self-localization Using Ranking -based Scene Descriptor","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2109.04569","title":"Open-World Distributed Robot Self-Localization with Transferable Visual Vocabulary and Both Absolute and Relative Features","created":"2021-09-09","cited_by_count":1,"area":null},{"id":"2112.13934","title":"RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2305.06141","title":"Active Semantic Localization with Graph Neural Embedding","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2601.20694","title":"Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?","created":"2026-01-28","cited_by_count":0,"area":null}],"next_cursor":null}