{"total":20,"rows":[{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2203.10124","title":"Approximate Function Evaluation via Multi-Armed Bandits","created":"2022-03-18","cited_by_count":4,"area":null},{"id":"2301.11442","title":"Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits","created":"2023-01-26","cited_by_count":3,"area":null},{"id":"2402.17732","title":"Batched Nonparametric Contextual Bandits","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2108.06812","title":"Batched Thompson Sampling for Multi-Armed Bandits","created":"2021-08-15","cited_by_count":2,"area":null},{"id":"2205.15891","title":"One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2303.11582","title":"Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches","created":"2023-03-21","cited_by_count":2,"area":null},{"id":"2410.08804","title":"Batched Energy-Entropy acquisition for Bayesian Optimization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2606.00984","title":"Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2210.12198","title":"Anonymous Bandits for Multi-User Systems","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2312.13875","title":"Best Arm Identification in Batched Multi-armed Bandit Problems","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2406.00424","title":"A Batch Sequential Halving Algorithm without Performance Degradation","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2506.03324","title":"Optimization of Epsilon-Greedy Exploration","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2312.15595","title":"Zero-Inflated Bandits","created":"2023-12-25","cited_by_count":0,"area":null},{"id":"2501.17370","title":"Breaking the $\\log(1/\\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids","created":"2025-01-29","cited_by_count":0,"area":null},{"id":"2511.03708","title":"The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2512.05680","title":"Meta-Learning Multi-armed Bandits for Beam Tracking in 5G and 6G Networks","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2609.38914","title":"Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}