{"total":22,"rows":[{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2302.09739","title":"A Blackbox Approach to Best of Both Worlds in Bandits and Beyond","created":"2023-02-20","cited_by_count":30,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2110.13282","title":"The Pareto Frontier of model selection for general Contextual Bandits","created":"2021-10-25","cited_by_count":24,"area":null},{"id":"2202.06151","title":"Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits","created":"2022-02-12","cited_by_count":22,"area":null},{"id":"2202.05100","title":"Adaptively Exploiting d-Separators with Causal Bandits","created":"2022-02-10","cited_by_count":18,"area":null},{"id":"2212.03798","title":"Stochastic Rising Bandits","created":"2022-12-07","cited_by_count":18,"area":null},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"area":null},{"id":"2111.00781","title":"Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure","created":"2021-11-01","cited_by_count":14,"area":null},{"id":"2206.14912","title":"Best of Both Worlds Model Selection","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2306.02869","title":"Data-Driven Online Model Selection With Regret Guarantees","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2107.03455","title":"Model Selection for Generic Contextual Bandits","created":"2021-07-07","cited_by_count":8,"area":null},{"id":"2203.04274","title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2106.06483","title":"Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2111.04688","title":"Universal and data-adaptive algorithms for model selection in linear contextual bandits","created":"2021-11-08","cited_by_count":5,"area":null},{"id":"2304.13830","title":"Adaptation to Misspecified Kernel Regularity in Kernelised Bandits","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2110.01810","title":"Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess","created":"2021-10-05","cited_by_count":4,"area":null},{"id":"2407.00950","title":"Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2511.10619","title":"Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null}],"next_cursor":null}