{"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":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2302.08893","title":"Active learning for data streams: a survey","created":"2023-02-17","cited_by_count":29,"area":null},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28,"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":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","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":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2211.05632","title":"Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms","created":"2022-11-08","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":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","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":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"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":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2408.00465","title":"Infrequent Resolving Algorithm for Online Linear Programming","created":"2024-08-01","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":"2103.11370","title":"Online Convex Optimization with Continuous Switching Constraint","created":"2021-03-21","cited_by_count":6,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2302.14015","title":"CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2311.00973","title":"Federated Linear Bandits with Finite Adversarial Actions","created":"2023-11-02","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":"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":"2508.03072","title":"Achieving Limited Adaptivity for Multinomial Logistic Bandits","created":"2025-08-05","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":"2602.00417","title":"Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits","created":"2026-01-31","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":"2605.24803","title":"Active Learning for Stochastic Contextual Linear Bandits","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2605.30976","title":"Batched Stochastic Linear Bandits with 1-Bit Communication Constraints","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2103.09927","title":"Encrypted Linear Contextual Bandit","created":"2021-03-17","cited_by_count":0,"area":null},{"id":"2112.06424","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2305.11509","title":"From Random Search to Bandit Learning in Metric Measure Spaces","created":"2023-05-19","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":"2509.04194","title":"Stochastic Matching Bandits with Rare Optimization Updates","created":"2025-09-04","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":"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":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.01789","title":"Learning in Prophet Inequalities with Noisy Observations","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.31449","title":"Contextual Slate GLM Bandits with Limited Adaptivity","created":"2026-06-30","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}