{"total":20,"rows":[{"id":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"area":null},{"id":"2205.13451","title":"Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2103.04546","title":"Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games","created":"2021-03-08","cited_by_count":15,"area":null},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","cited_by_count":11,"area":null},{"id":"2206.04475","title":"Individually Fair Learning with One-Sided Feedback","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2604.24555","title":"Efficient learning by implicit exploration in bandit problems with side observations","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2409.20440","title":"Optimism in the Face of Ambiguity Principle for Multi-Armed Bandits","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2207.05437","title":"Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2412.06079","title":"Learning from Snapshots of Discrete and Continuous Data Streams","created":"2024-12-08","cited_by_count":2,"area":null},{"id":"2604.25269","title":"Online combinatorial optimization with stochastic decision sets and adversarial losses","created":"2026-04-28","cited_by_count":2,"area":null},{"id":"2310.00562","title":"Discrete Choice Multi-Armed Bandits","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2604.25271","title":"Online learning with Erd\\H{o}s-R\\'enyi side-observation graphs","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2101.11443","title":"Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2107.03003","title":"Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2210.05789","title":"Trading Off Resource Budgets for Improved Regret Bounds","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2210.05977","title":"BORA: Bayesian Optimization for Resource Allocation","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2510.03979","title":"Beyond Softmax: A New Perspective on Gradient Bandits","created":"2025-10-04","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":"2510.21431","title":"Oracle-Efficient Combinatorial Semi-Bandits","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","cited_by_count":0,"area":null}],"next_cursor":null}