{"total":67,"rows":[{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"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":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"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":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40,"area":null},{"id":"2106.04117","title":"The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition","created":"2021-06-08","cited_by_count":40,"area":null},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40,"area":null},{"id":"2112.03432","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","created":"2021-12-07","cited_by_count":38,"area":null},{"id":"2104.11186","title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret","created":"2021-04-22","cited_by_count":34,"area":null},{"id":"2107.01264","title":"Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning","created":"2021-07-02","cited_by_count":34,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2105.14363","title":"On the Theory of Reinforcement Learning with Once-per-Episode Feedback","created":"2021-05-29","cited_by_count":32,"area":null},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27,"area":null},{"id":"2106.14352","title":"Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning","created":"2021-06-28","cited_by_count":22,"area":null},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"area":null},{"id":"2102.06875","title":"Improved Corruption Robust Algorithms for Episodic Reinforcement Learning","created":"2021-02-13","cited_by_count":20,"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":"2110.14798","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17,"area":null},{"id":"2107.08622","title":"Provably Efficient Multi-Task Reinforcement Learning with Model Transfer","created":"2021-07-19","cited_by_count":16,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2106.13013","title":"A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15,"area":null},{"id":"2112.09859","title":"Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP","created":"2021-12-18","cited_by_count":14,"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":"2110.13052","title":"Can Q-Learning be Improved with Advice?","created":"2021-10-25","cited_by_count":13,"area":null},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","cited_by_count":12,"area":null},{"id":"2110.15843","title":"Adaptive Discretization in Online Reinforcement Learning","created":"2021-10-29","cited_by_count":12,"area":null},{"id":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2108.05439","title":"Gap-Dependent Unsupervised Exploration for Reinforcement Learning","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2205.11168","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2306.02399","title":"Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures","created":"2023-06-04","cited_by_count":8,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2107.00685","title":"Gap-Dependent Bounds for Two-Player Markov Games","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2201.08536","title":"Instance-Dependent Confidence and Early Stopping for Reinforcement Learning","created":"2022-01-21","cited_by_count":5,"area":null},{"id":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2210.11604","title":"Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes","created":"2022-10-20","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":"2506.06521","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2210.13075","title":"Hardness in Markov Decision Processes: Theory and Practice","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2203.03110","title":"Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2404.00195","title":"Multiple-policy Evaluation via Density Estimation","created":"2024-03-29","cited_by_count":2,"area":null},{"id":"2110.05724","title":"Query-Reward Tradeoffs in Multi-Armed Bandits","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","cited_by_count":0,"area":null},{"id":"2301.04268","title":"Adversarial Online Multi-Task Reinforcement Learning","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2505.12037","title":"Adaptive Resolving Methods for Markov Decision Processes with Function Approximations","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2605.04979","title":"On-line Learning in Tree MDPs by Treating Policies as Bandit Arms","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2608.01378","title":"When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}