{"total":13,"rows":[{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2205.14090","title":"Surrogate modeling for Bayesian optimization beyond a single Gaussian process","created":"2022-05-27","cited_by_count":22,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2310.07518","title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2205.06326","title":"Multi-Environment Meta-Learning in Stochastic Linear Bandits","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2407.06329","title":"Solving Multi-Model MDPs by Coordinate Ascent and Dynamic Programming","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2502.01226","title":"Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2309.06349","title":"Generalized Regret Analysis of Thompson Sampling using Fractional Posteriors","created":"2023-09-12","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":"2602.17958","title":"Bayesian Online Model Selection","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2609.01999","title":"Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}