{"total":27,"rows":[{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2103.02827","title":"On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk","created":"2021-03-04","cited_by_count":20,"area":null},{"id":"2201.11463","title":"Quantile-Based Policy Optimization for Reinforcement Learning","created":"2022-01-27","cited_by_count":8,"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":"2209.10444","title":"Off-Policy Risk Assessment in Markov Decision Processes","created":"2022-09-21","cited_by_count":7,"area":null},{"id":"2309.06375","title":"Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models","created":"2023-09-08","cited_by_count":7,"area":null},{"id":"2107.04422","title":"Policy Gradient Methods for Distortion Risk Measures","created":"2021-07-09","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2206.13648","title":"Supervised Learning with General Risk Functionals","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2208.09106","title":"A Risk-Sensitive Approach to Policy Optimization","created":"2022-08-19","cited_by_count":6,"area":null},{"id":"2305.11476","title":"Learning Diverse Risk Preferences in Population-based Self-play","created":"2023-05-19","cited_by_count":6,"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":"2305.07248","title":"Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2107.02283","title":"Clustering Structure of Microstructure Measures","created":"2021-07-05","cited_by_count":3,"area":null},{"id":"2407.18422","title":"A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2104.00540","title":"Reinforcement Learning Beyond Expectation","created":"2021-03-29","cited_by_count":2,"area":null},{"id":"2106.12700","title":"An Efficient Group-based Search Engine Marketing System for E-Commerce","created":"2021-06-24","cited_by_count":2,"area":null},{"id":"2202.11046","title":"A policy gradient approach for optimization of smooth risk measures","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2209.10792","title":"Deep Learning Based Page Creation for Improving E-Commerce Organic Search Traffic","created":"2022-09-22","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":"2205.14545","title":"Functional Linear Regression of Cumulative Distribution Functions","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2605.19674","title":"Beyond Rational Illusion: Behaviorally Realistic Strategic Classification","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2101.03497","title":"Joint Prediction of Remaining Useful Life and Failure Type of Train Wheelsets: A Multi-task Learning Approach","created":"2021-01-10","cited_by_count":0,"area":null},{"id":"2310.05179","title":"DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption","created":"2023-10-08","cited_by_count":0,"area":null},{"id":"2510.04563","title":"Stochastic Approximation Methods for Distortion Risk Measure Optimization","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2605.15620","title":"Pessimistic Risk-Aware Policy Learning in Contextual Bandits","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.19883","title":"Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}