{"total":19,"rows":[{"id":"2302.03201","title":"Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR","created":"2023-02-07","cited_by_count":32,"area":null},{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2201.11921","title":"Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits","created":"2022-01-28","cited_by_count":18,"area":null},{"id":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"area":null},{"id":"2211.14768","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2205.05843","title":"A Survey of Risk-Aware Multi-Armed Bandits","created":"2022-05-12","cited_by_count":8,"area":null},{"id":"2410.03284","title":"uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2111.08805","title":"Online Estimation and Optimization of Utility-Based Shortfall Risk","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2209.02211","title":"Multi-Armed Bandits with Self-Information Rewards","created":"2022-09-06","cited_by_count":5,"area":null},{"id":"2103.05059","title":"Bias-Corrected Peaks-Over-Threshold Estimation of the CVaR","created":"2021-03-08","cited_by_count":3,"area":null},{"id":"2204.09833","title":"Sample-Based Bounds for Coherent Risk Measures: Applications to Policy Synthesis and Verification","created":"2022-04-21","cited_by_count":3,"area":null},{"id":"2406.05710","title":"Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2503.08896","title":"Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2102.12090","title":"Continuous Mean-Covariance Bandits","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2112.01141","title":"Risk-Aware Algorithms for Combinatorial Semi-Bandits","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2405.20933","title":"Concentration Bounds for Optimized Certainty Equivalent Risk Estimation","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2406.06552","title":"Optimizing Sharpe Ratio: Risk-Adjusted Decision-Making in Multi-Armed Bandits","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2505.11985","title":"Variance-Optimal Arm Selection: Misallocation Minimization and Best Arm Identification","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2604.22140","title":"Concave Statistical Utility Maximization Bandits via Influence-Function Gradients","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":null}