{"total":41,"rows":[{"id":"2206.10786","title":"Generative Pretraining for Black-Box Optimization","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2106.02126","title":"A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms","created":"2021-06-03","cited_by_count":30,"area":null},{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2103.12452","title":"Bandits with many optimal arms","created":"2021-03-23","cited_by_count":17,"area":null},{"id":"2307.10890","title":"Player-optimal Stable Regret for Bandit Learning in Matching Markets","created":"2023-07-20","cited_by_count":17,"area":null},{"id":"2109.14429","title":"Minimal Expected Regret in Linear Quadratic Control","created":"2021-09-29","cited_by_count":13,"area":null},{"id":"2210.16386","title":"Non-Stationary Bandits with Auto-Regressive Temporal Dependency","created":"2022-10-28","cited_by_count":10,"area":null},{"id":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2105.10721","title":"From Finite to Countable-Armed Bandits","created":"2021-05-22","cited_by_count":8,"area":null},{"id":"2310.14129","title":"Optimal Batched Best Arm Identification","created":"2023-10-21","cited_by_count":8,"area":null},{"id":"2401.01528","title":"Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2410.04376","title":"Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning","created":"2024-10-06","cited_by_count":7,"area":null},{"id":"2205.11788","title":"Meta Policy Learning for Cold-Start Conversational Recommendation","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2502.17175","title":"Linear Bandits on Ellipsoids: Minimax Optimal Algorithms","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2603.10219","title":"A Diffusion Analysis of Policy Gradient for Stochastic Bandits","created":"2026-03-10","cited_by_count":4,"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":"2404.17398","title":"Online Policy Learning and Inference by Matrix Completion","created":"2024-04-26","cited_by_count":3,"area":null},{"id":"2101.01572","title":"Sequential Choice Bandits with Feedback for Personalizing users' experience","created":"2021-01-05","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":"2502.04673","title":"Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2106.02552","title":"Active Covering","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2110.02690","title":"Tuning Confidence Bound for Stochastic Bandits with Bandit Distance","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2302.09700","title":"Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty","created":"2023-02-20","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":"2312.07285","title":"Forced Exploration in Bandit Problems","created":"2023-12-12","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":"2506.14518","title":"Two-Player Zero-Sum Games with Bandit Feedback","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2510.05023","title":"Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2510.12152","title":"Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2211.08311","title":"On Penalization in Stochastic Multi-armed Bandits","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2310.14751","title":"Efficient and Interpretable Bandit Algorithms","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2310.17538","title":"Little Exploration is All You Need","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2510.26000","title":"Infrequent Exploration in Linear Bandits","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2512.17462","title":"Behavioural Effects of Agentic Messaging: A Case Study on a Financial Service Application","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2605.19584","title":"Online Market Making and the Value of Observing the Order Book","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.01799","title":"Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.20628","title":"Human Decision-Making with AI Assistance under Correlated Features","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.23432","title":"Experimentation and Commitment under Reward Shifts","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2609.22690","title":"Multi-Armed Bernoulli Bandits via Minimax Single-Arm Stopping","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.32149","title":"A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.19804","title":"Efficient contextual partial monitoring with general function approximation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}