{"total":26,"rows":[{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2111.07430","title":"Safe Online Convex Optimization with Unknown Linear Safety Constraints","created":"2021-11-14","cited_by_count":13,"area":null},{"id":"2102.10156","title":"Learning to Persuade on the Fly: Robustness Against Ignorance","created":"2021-02-19","cited_by_count":12,"area":null},{"id":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2301.11547","title":"Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation","created":"2023-01-27","cited_by_count":6,"area":null},{"id":"2111.13415","title":"ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2311.04338","title":"Convex Methods for Constrained Linear Bandits","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2302.12320","title":"Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems","created":"2023-02-23","cited_by_count":4,"area":null},{"id":"2309.08709","title":"Price of Safety in Linear Best Arm Identification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2401.11563","title":"Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2112.06728","title":"Safe Linear Leveling Bandits","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2211.01561","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","created":"2022-11-03","cited_by_count":1,"area":null},{"id":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","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":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2311.04731","title":"Robust Best-arm Identification in Linear Bandits","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2504.16371","title":"The Safety-Privacy Tradeoff in Linear Bandits","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2507.18975","title":"Secure Best Arm Identification in the Presence of a Copycat","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2602.05019","title":"A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2605.12176","title":"Multi-Task Representation Learning for Conservative Linear Bandits","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}