{"total":17,"rows":[{"id":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2109.08792","title":"Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making","created":"2021-09-18","cited_by_count":11,"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":"2309.00557","title":"Concentrated Differential Privacy for Bandits","created":"2023-09-01","cited_by_count":10,"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":"2307.02108","title":"Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2302.04441","title":"Multi-task Representation Learning for Pure Exploration in Linear Bandits","created":"2023-02-09","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":"2302.14015","title":"CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2207.05250","title":"Efficient Real-world Testing of Causal Decision Making via Bayesian Experimental Design for Contextual Optimisation","created":"2022-07-12","cited_by_count":3,"area":null},{"id":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2210.12198","title":"Anonymous Bandits for Multi-User Systems","created":"2022-10-21","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":"2606.17515","title":"Anytime-valid Optimal Policy Identification","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2302.09451","title":"Estimating Optimal Policy Value in General Linear Contextual Bandits","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2502.05498","title":"Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations","created":"2025-02-08","cited_by_count":0,"area":null}],"next_cursor":null}