{"total":19,"rows":[{"id":"2206.05979","title":"Top Two Algorithms Revisited","created":"2022-06-13","cited_by_count":34,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2412.06126","title":"UCB algorithms for multi-armed bandits: Precise regret and adaptive inference","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2206.03520","title":"Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2210.00895","title":"On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits","created":"2022-09-30","cited_by_count":8,"area":null},{"id":"2105.12978","title":"A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits","created":"2021-05-27","cited_by_count":7,"area":null},{"id":"2107.11419","title":"Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits","created":"2021-07-23","cited_by_count":7,"area":null},{"id":"2602.07472","title":"Bandit Allocational Instability","created":"2026-02-07","cited_by_count":3,"area":null},{"id":"2304.03056","title":"Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms","created":"2023-04-06","cited_by_count":2,"area":null},{"id":"2304.14989","title":"Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards","created":"2023-04-28","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":"2404.10207","title":"HELLINGER-UCB: A novel algorithm for stochastic multi-armed bandit problem and cold start problem in recommender system","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2410.02279","title":"On Lai's Upper Confidence Bound in Multi-Armed Bandits","created":"2024-10-03","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":"2310.17538","title":"Little Exploration is All You Need","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2407.05704","title":"Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2508.07991","title":"Sharper Perturbed-Kullback-Leibler Exponential Tail Bounds for Beta and Dirichlet Distributions","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2609.22690","title":"Multi-Armed Bernoulli Bandits via Minimax Single-Arm Stopping","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}