3 papers
math.NA2026
Deep Policy Iteration for High-Dimensional Mean-Field Games with Regenerative Reformulation
Shuixin Fang, Shupeng Wang, Zhen Wu +2
This paper develops a deep policy iteration method for high-dimensional finite-horizon mean-field games (MFG). We reformulate the game as a regenerative problem with deterministic…
cs.LG2024
Risk-sensitive Markov Decision Process and Learning under General Utility Functions
Zhengqi Wu, Renyuan Xu
Reinforcement Learning (RL) has gained substantial attention across diverse application domains and theoretical investigations. Existing literature on RL theory largely focuses on…
math.OC2024
Inference of Utilities and Time Preference in Sequential Decision-Making
Haoyang Cao, Zhengqi Wu, Renyuan Xu
This paper introduces a novel stochastic control framework to enhance the capabilities of automated investment managers, or robo-advisors, by accurately inferring clients' investme…