{"total":19,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2112.02856","title":"Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback","created":"2021-12-06","cited_by_count":15,"area":null},{"id":"2103.04550","title":"No Weighted-Regret Learning in Adversarial Bandits with Delays","created":"2021-03-08","cited_by_count":12,"area":null},{"id":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2209.11817","title":"An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret","created":"2022-09-23","cited_by_count":10,"area":null},{"id":"2402.09152","title":"Improved Regret for Bandit Convex Optimization with Delayed Feedback","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2108.07406","title":"From the Greene--Wu Convolution to Gradient Estimation over Riemannian Manifolds","created":"2021-08-17","cited_by_count":6,"area":null},{"id":"2109.05829","title":"Zeroth-order non-convex learning via hierarchical dual averaging","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2102.07387","title":"Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization","created":"2021-02-15","cited_by_count":3,"area":null},{"id":"2602.02634","title":"A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2202.06150","title":"Adaptive Bandit Convex Optimization with Heterogeneous Curvature","created":"2022-02-12","cited_by_count":2,"area":null},{"id":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2406.02103","title":"A Bayesian Approach to Online Planning","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2510.00602","title":"Multi-Agent Stage-wise Conservative Linear Bandits","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2606.11711","title":"Capacity-Constrained Online Convex Optimization with Delayed Feedback","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2409.15680","title":"Distributed Online Bandit Nonconvex Optimization with One-Point Residual Feedback via Dynamic Regret","created":"2024-09-24","cited_by_count":0,"area":null}],"next_cursor":null}