Gao-Zhan Wang

Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence

This work takes the exploratory, reinforcement learning (RL) framework of Wang, Zariphopoulou, and Zhou with relaxed controls and entropy regularization with the objective to develop theoretically grounded, efficient and scalable RL algorithms to learn both the optimal value functions and optimal feedback control polic...