{"total":45,"rows":[{"id":"2102.05858","title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","created":"2021-02-11","cited_by_count":48,"area":null},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2209.02570","title":"When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits","created":"2022-09-06","cited_by_count":28,"area":null},{"id":"2106.02553","title":"Fair Exploration via Axiomatic Bargaining","created":"2021-06-04","cited_by_count":22,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2110.14798","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2205.14775","title":"An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge","created":"2022-05-29","cited_by_count":17,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17,"area":null},{"id":"2202.04294","title":"Optimal Clustering with Bandit Feedback","created":"2022-02-09","cited_by_count":15,"area":null},{"id":"2302.12370","title":"Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds","created":"2023-02-24","cited_by_count":14,"area":null},{"id":"2205.01257","title":"Norm-Agnostic Linear Bandits","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2303.06825","title":"Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm","created":"2023-03-13","cited_by_count":12,"area":null},{"id":"2302.08631","title":"Practical Contextual Bandits with Feedback Graphs","created":"2023-02-17","cited_by_count":11,"area":null},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2110.13876","title":"Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2502.08870","title":"When and why randomised exploration works (in linear bandits)","created":"2025-02-13","cited_by_count":8,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2406.04137","title":"Optimal Batched Linear Bandits","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2307.07320","title":"Adaptive Linear Estimating Equations","created":"2023-07-14","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2104.03860","title":"Incentivizing Exploration in Linear Bandits under Information Gap","created":"2021-04-08","cited_by_count":5,"area":null},{"id":"2305.17402","title":"Learning and Collusion in Multi-unit Auctions","created":"2023-05-27","cited_by_count":5,"area":null},{"id":"2112.01452","title":"Indexed Minimum Empirical Divergence for Unimodal Bandits","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2602.06348","title":"Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2203.09784","title":"The price of unfairness in linear bandits with biased feedback","created":"2022-03-18","cited_by_count":3,"area":null},{"id":"2306.14872","title":"Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2310.00532","title":"Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference","created":"2023-10-01","cited_by_count":3,"area":null},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2212.09429","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2312.16489","title":"Best-of-Both-Worlds Linear Contextual Bandits","created":"2023-12-27","cited_by_count":2,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2405.15200","title":"Indexed Minimum Empirical Divergence-Based Algorithms for Linear Bandits","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2510.17103","title":"Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2202.11735","title":"Truncated LinUCB for Stochastic Linear Bandits","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2402.15127","title":"Asymptotically and Minimax Optimal Regret Bounds for Multi-Armed Bandits with Abstention","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2506.02386","title":"Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2509.19901","title":"Pure Exploration via Frank-Wolfe Self-Play","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2111.04915","title":"Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers","created":"2021-11-09","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":"2509.05864","title":"Beyond ATE: Multi-Criteria Design for A/B Testing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.07424","title":"Best-of-Both Worlds for linear contextual bandits with paid observations","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2606.09802","title":"Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2610.06213","title":"Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}