{"total":47,"rows":[{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2110.07788","title":"Gaussian Process Bandit Optimization with Few Batches","created":"2021-10-15","cited_by_count":57,"area":null},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2106.02900","title":"Differentially Private Multi-Armed Bandits in the Shuffle Model","created":"2021-06-05","cited_by_count":24,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2210.01898","title":"Replicable Bandits","created":"2022-10-04","cited_by_count":22,"area":null},{"id":"2110.09722","title":"Lipschitz Bandits with Batched Feedback","created":"2021-10-19","cited_by_count":21,"area":null},{"id":"2106.01420","title":"Parallelizing Thompson Sampling","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2102.09864","title":"An Algorithm for Stochastic and Adversarial Bandits with Switching Costs","created":"2021-02-19","cited_by_count":19,"area":null},{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2207.03445","title":"Differentially Private Stochastic Linear Bandits: (Almost) for Free","created":"2022-07-07","cited_by_count":19,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2111.06067","title":"Solving Multi-Arm Bandit Using a Few Bits of Communication","created":"2021-11-11","cited_by_count":16,"area":null},{"id":"2206.03098","title":"Better Best of Both Worlds Bounds for Bandits with Switching Costs","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2202.10660","title":"Batched Dueling Bandits","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2110.08057","title":"Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits","created":"2021-10-15","cited_by_count":9,"area":null},{"id":"2302.01539","title":"A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2202.07079","title":"Synthetically Controlled Bandits","created":"2022-02-14","cited_by_count":8,"area":null},{"id":"2406.04137","title":"Optimal Batched Linear Bandits","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2401.12722","title":"Falcon: Fair Active Learning using Multi-armed Bandits","created":"2024-01-23","cited_by_count":6,"area":null},{"id":"2210.06719","title":"Reward Imputation with Sketching for Contextual Batched Bandits","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2202.06657","title":"The Impact of Batch Learning in Stochastic Linear Bandits","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2308.04314","title":"Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2407.00571","title":"Adversarial Online Learning with Temporal Feedback Graphs","created":"2024-06-30","cited_by_count":3,"area":null},{"id":"2603.12627","title":"Batched Kernelized Bandits: Refinements and Extensions","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2209.12108","title":"An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem","created":"2022-09-25","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":"2307.11655","title":"Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2402.07391","title":"Replicability is Asymptotically Free in Multi-armed Bandits","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2405.05733","title":"Batched Stochastic Bandit for Nondegenerate Functions","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2507.08438","title":"Optimal and Practical Batched Linear Bandit Algorithm","created":"2025-07-11","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":"2111.02071","title":"The Impact of Batch Learning in Stochastic Bandits","created":"2021-11-03","cited_by_count":1,"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":"2406.00424","title":"A Batch Sequential Halving Algorithm without Performance Degradation","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2505.10498","title":"Batched Nonparametric Bandits via k-Nearest Neighbor UCB","created":"2025-05-15","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":"2506.19752","title":"On the necessity of adaptive regularisation:Optimal anytime online learning on $\\boldsymbol{\\ell_p}$-balls","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2603.13742","title":"Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Bandits","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2304.11741","title":"Robust and differentially private stochastic linear bandits","created":"2023-04-23","cited_by_count":0,"area":null},{"id":"2502.07514","title":"A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2510.03798","title":"Batched Bandits with Heavy-Tailed Rewards","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2606.27448","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.07922","title":"Memory--Batch Tradeoffs in Lipschitz Bandits","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}