{"total":11,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2110.12727","title":"Learning Stochastic Shortest Path with Linear Function Approximation","created":"2021-10-25","cited_by_count":23,"area":null},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2206.06841","title":"Robust Reinforcement Learning with Distributional Risk-averse formulation","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2206.14666","title":"Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning","created":"2022-06-29","cited_by_count":9,"area":null},{"id":"2303.15216","title":"Robust Risk-Aware Option Hedging","created":"2023-03-27","cited_by_count":9,"area":null},{"id":"2208.09106","title":"A Risk-Sensitive Approach to Policy Optimization","created":"2022-08-19","cited_by_count":6,"area":null},{"id":"2212.14670","title":"Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization","created":"2022-12-11","cited_by_count":1,"area":null},{"id":"2301.01045","title":"Risk-Averse MDPs under Reward Ambiguity","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2305.06796","title":"Towards Theoretical Understanding of Data-Driven Policy Refinement","created":"2023-05-11","cited_by_count":0,"area":null},{"id":"2410.23029","title":"Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning","created":"2024-10-30","cited_by_count":0,"area":null}],"next_cursor":null}