Convergence Analysis of Discrete Sampling in Continuous-Time Reinforcement Learning and High-Dimensional Numerical Integration
Du Ouyang, Tsinghua
Stochastic policies (also known as relaxed controls) are widely used in continuous-time Reinforcement Learning (RL) algorithms. However, a...
On hypoellipticity of degenerate operators in testing and detection problems
Yuqiong Wang, UM.
We study a class of degenerate diffusion generators that arise in sequential testing and quickest detection problems with partial...
Mean-field analysis for the training of overparameterized Deep ResNet
Zhiyan Ding, UM
In this talk, I will present the mean-field analysis framework for overparameterized Deep ResNets. I will first establish the rigorous...
Learning MFG via MFAC Flow
Ruimeng Hu, UCSB
We introduce the Mean-Field Actor-Critic (MFAC) flow, a continuous-time learning dynamics for solving mean-field games (MFGs), drawing on...
