{"total":26,"rows":[{"id":"2106.15648","title":"Learning to Map for Active Semantic Goal Navigation","created":"2021-06-29","cited_by_count":50,"area":null},{"id":"2112.13414","title":"Reinforcement Learning with Dynamic Convex Risk Measures","created":"2021-12-26","cited_by_count":21,"area":null},{"id":"2109.13595","title":"The Fragility of Optimized Bandit Algorithms","created":"2021-09-28","cited_by_count":17,"area":null},{"id":"2402.06276","title":"Safe Active Learning for Time-Series Modeling with Gaussian Processes","created":"2024-02-09","cited_by_count":12,"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":"2105.04816","title":"Spectral risk-based learning using unbounded losses","created":"2021-05-11","cited_by_count":8,"area":null},{"id":"2111.02907","title":"Model-Free Risk-Sensitive Reinforcement Learning","created":"2021-11-04","cited_by_count":7,"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":"2206.03019","title":"The Survival Bandit Problem","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2201.07139","title":"Safe Online Bid Optimization with Return on Investment and Budget Constraints","created":"2022-01-18","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":"2105.06960","title":"Thompson Sampling for Gaussian Entropic Risk Bandits","created":"2021-05-14","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":"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":"2405.10581","title":"Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","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":"2208.06245","title":"Understanding the stochastic dynamics of sequential decision-making processes: A path-integral analysis of multi-armed bandits","created":"2022-08-11","cited_by_count":0,"area":null},{"id":"2305.09626","title":"Balancing Risk and Reward: An Automated Phased Release Strategy","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2310.19821","title":"A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.20403","title":"Risk-Averse Wasserstein Distributionally Robust Online Learning","created":"2026-02-23","cited_by_count":0,"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},{"id":"2605.07115","title":"Conformal-Style Quantile Analyses for Stochastic Bandits","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}