{"total":26,"rows":[{"id":"2206.05979","title":"Top Two Algorithms Revisited","created":"2022-06-13","cited_by_count":34,"area":null},{"id":"2109.13595","title":"The Fragility of Optimized Bandit Algorithms","created":"2021-09-28","cited_by_count":17,"area":null},{"id":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2401.11665","title":"Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo","created":"2024-01-22","cited_by_count":10,"area":null},{"id":"2108.11345","title":"A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits","created":"2021-08-25","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":"2111.09724","title":"From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2206.02969","title":"A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2302.01544","title":"Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits","created":"2023-02-03","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":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2306.07059","title":"A Distribution Optimization Framework for Confidence Bounds of Risk Measures","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2606.05551","title":"Conformal Risk-Averse Decision Making with Action Conditional Guarantee","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2109.13977","title":"Risk averse non-stationary multi-armed bandits","created":"2021-09-28","cited_by_count":1,"area":null},{"id":"2206.12463","title":"Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2209.07154","title":"Risk-aware linear bandits with convex loss","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2508.13749","title":"Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2605.12646","title":"Learning to Decide with AI Assistance under Human-Alignment","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2210.04537","title":"Towards an efficient and risk aware strategy for guiding farmers in identifying best crop management","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2503.21640","title":"Towards Fully Automated Decision-Making Systems for Greenhouse Control: Challenges and Opportunities","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2509.01924","title":"Non-Linear Model-Based Sequential Decision-Making in Agriculture","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.04728","title":"EVaR-Optimal Arm Identification in Bandits","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2604.12519","title":"Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.09191","title":"Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}