{"total":27,"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":"2202.00150","title":"Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints","created":"2022-01-31","cited_by_count":29,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2209.13694","title":"Safe Linear Bandits over Unknown Polytopes","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2209.01126","title":"Learning While Scheduling in Multi-Server Systems with Unknown Statistics: MaxWeight with Discounted UCB","created":"2022-09-02","cited_by_count":8,"area":null},{"id":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2407.01795","title":"Honor Among Bandits: No-Regret Learning for Online Fair Division","created":"2024-07-01","cited_by_count":7,"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":"2302.02426","title":"Online Nonstochastic Control with Adversarial and Static Constraints","created":"2023-02-05","cited_by_count":5,"area":null},{"id":"2106.05165","title":"A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2501.00924","title":"On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2501.07022","title":"Improved Regret Bounds for Online Fair Division with Bandit Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2301.13791","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2306.13440","title":"Trading-off price for data quality to achieve fair online allocation","created":"2023-06-23","cited_by_count":2,"area":null},{"id":"2405.15090","title":"Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2503.03195","title":"Online Bidding under RoS Constraints without Knowing the Value","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2506.03062","title":"Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2309.07176","title":"Mind the Gap: Optimal and Equitable Encouragement Policies","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2410.03651","title":"Minimax-optimal trust-aware multi-armed bandits","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2412.03983","title":"Safe and Efficient Online Convex Optimization with Linear Budget Constraints and Partial Feedback","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2502.07397","title":"Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2509.12457","title":"On the Regularity and Fairness of Combinatorial Multi-Armed Bandit","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2601.05956","title":"On the Robustness of Age for Learning-Based Wireless Scheduling in Unknown Environments","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2603.04247","title":"Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback","created":"2026-03-04","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}