{"total":47,"rows":[{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"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":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2110.04645","title":"Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning","created":"2021-10-09","cited_by_count":53,"area":null},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"area":null},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"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":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40,"area":null},{"id":"2305.10697","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","created":"2023-05-18","cited_by_count":36,"area":null},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"area":null},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2301.13446","title":"Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments","created":"2023-01-31","cited_by_count":19,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2203.03684","title":"Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets","created":"2022-03-07","cited_by_count":16,"area":null},{"id":"2105.08285","title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","created":"2021-05-18","cited_by_count":15,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2302.12456","title":"Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs","created":"2023-02-24","cited_by_count":9,"area":null},{"id":"2202.01292","title":"Improved Regret for Differentially Private Exploration in Linear MDP","created":"2022-02-02","cited_by_count":8,"area":null},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2306.09554","title":"Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2410.22908","title":"Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2102.11448","title":"MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning","created":"2021-02-23","cited_by_count":4,"area":null},{"id":"2302.04374","title":"Near-Optimal Adversarial Reinforcement Learning with Switching Costs","created":"2023-02-08","cited_by_count":4,"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":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2301.11442","title":"Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits","created":"2023-01-26","cited_by_count":3,"area":null},{"id":"2402.17732","title":"Batched Nonparametric Contextual Bandits","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2108.06812","title":"Batched Thompson Sampling for Multi-Armed Bandits","created":"2021-08-15","cited_by_count":2,"area":null},{"id":"2205.15891","title":"One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2103.09927","title":"Encrypted Linear Contextual Bandit","created":"2021-03-17","cited_by_count":0,"area":null},{"id":"2112.06424","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2305.02058","title":"Human Machine Co-adaption Interface via Cooperation Markov Decision Process System","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2306.08762","title":"Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2503.07319","title":"Human Machine Co-Adaptation Model and Its Convergence Analysis","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2511.03708","title":"The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2606.02363","title":"Minimax-Optimal Policy Regret in Partially Observable Markov Games","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}