{"total":20,"rows":[{"id":"2102.05858","title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","created":"2021-02-11","cited_by_count":48,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2110.08627","title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2212.00884","title":"Pareto Regret Analyses in Multi-objective Multi-armed Bandit","created":"2022-12-01","cited_by_count":13,"area":null},{"id":"2106.04700","title":"Scale Free Adversarial Multi Armed Bandits","created":"2021-06-08","cited_by_count":12,"area":null},{"id":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2205.13044","title":"Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2301.12595","title":"Adversarial Attacks on Adversarial Bandits","created":"2023-01-30","cited_by_count":6,"area":null},{"id":"2110.14485","title":"Fast rates for prediction with limited expert advice","created":"2021-10-27","cited_by_count":4,"area":null},{"id":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"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":"2210.02256","title":"Constant regret for sequence prediction with limited advice","created":"2022-10-05","cited_by_count":2,"area":null},{"id":"2303.08102","title":"Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice","created":"2023-03-14","cited_by_count":2,"area":null},{"id":"2505.20010","title":"Data-Dependent Regret Bounds for Constrained MABs","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2510.05808","title":"Risk level dependent Minimax Quantile lower bounds for Interactive Statistical Decision Making","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2605.08287","title":"Multi-Armed Bandits With Best-Action Queries","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2103.04215","title":"Hierarchical Causal Bandit","created":"2021-03-07","cited_by_count":0,"area":null},{"id":"2410.03651","title":"Minimax-optimal trust-aware multi-armed bandits","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2606.00835","title":"Online Packet Scheduling with Deadlines and Learning","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.23414","title":"Leveraging Similarities in Multi-Armed Bandits","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}