{"total":16,"rows":[{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"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":"2104.14527","title":"Online certification of preference-based fairness for personalized recommender systems","created":"2021-04-29","cited_by_count":22,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9,"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":"2104.08615","title":"Conservative Contextual Combinatorial Cascading Bandit","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"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":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2103.03307","title":"Conservative Optimistic Policy Optimization via Multiple Importance Sampling","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2302.03784","title":"Leveraging User-Triggered Supervision in Contextual Bandits","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","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":"2609.39106","title":"Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}