{"total":15,"rows":[{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2105.09232","title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","created":"2021-05-19","cited_by_count":12,"area":null},{"id":"2202.11474","title":"Residual Bootstrap Exploration for Stochastic Linear Bandit","created":"2022-02-23","cited_by_count":8,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2102.00966","title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search","created":"2021-02-01","cited_by_count":5,"area":null},{"id":"2211.13032","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2410.23423","title":"Dynamic Information Sub-Selection for Decision Support","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2107.08383","title":"GuideBoot: Guided Bootstrap for Deep Contextual Bandits","created":"2021-07-18","cited_by_count":0,"area":null},{"id":"2404.03419","title":"Integrating Hyperparameter Search into Model-Free AutoML with Context-Free Grammars","created":"2024-04-04","cited_by_count":0,"area":null},{"id":"2503.04518","title":"Leveraging priors on distribution functions for multi-arm bandits","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2505.04200","title":"Estimating Causal Effects in Networks with Cluster-Based Bandits","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2605.07775","title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}