{"total":25,"rows":[{"id":"2106.01420","title":"Parallelizing Thompson Sampling","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2101.09855","title":"Weak Signal Asymptotics for Sequentially Randomized Experiments","created":"2021-01-25","cited_by_count":14,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2310.04550","title":"Module-wise Adaptive Distillation for Multimodality Foundation Models","created":"2023-10-06","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":"2111.02314","title":"Online Learning of Energy Consumption for Navigation of Electric Vehicles","created":"2021-11-03","cited_by_count":7,"area":null},{"id":"2102.09488","title":"A Bit Better? Quantifying Information for Bandit Learning","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2306.01990","title":"Incentivizing Exploration with Linear Contexts and Combinatorial Actions","created":"2023-06-03","cited_by_count":5,"area":null},{"id":"2102.05502","title":"On the Suboptimality of Thompson Sampling in High Dimensions","created":"2021-02-10","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2302.01544","title":"Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2402.13338","title":"Incentivized Exploration via Filtered Posterior Sampling","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2308.14350","title":"Simple Modification of the Upper Confidence Bound Algorithm by Generalized Weighted Averages","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2405.04910","title":"Learning with Posterior Sampling for Revenue Management under Time-varying Demand","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2207.06917","title":"Online Bayesian Meta-Learning for Cognitive Tracking Radar","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2301.07156","title":"A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2303.03348","title":"Thompson Sampling for Linear Bandit Problems with Normal-Gamma Priors","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2306.16578","title":"Allocating Divisible Resources on Arms with Unknown and Random Rewards","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2310.10107","title":"Posterior Sampling-based Online Learning for Episodic POMDPs","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2506.01685","title":"Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts","created":"2025-06-02","cited_by_count":0,"area":null}],"next_cursor":null}