Data-Adaptive Probabilistic Likelihood Approximation for Ordinary Differential Equations

1 code implementation • 8 Jun 2023 • Mohan Wu, Martin Lysy

This produces deep local maxima in the likelihood function -- a problem which existing probabilistic solvers have yet to resolve.

Reinforcement Learning in Computing and Network Convergence Orchestration

no code implementations • 22 Sep 2022 • Aidong Yang, Mohan Wu, Boquan Cheng, Xiaozhou Ye, Ye Ouyang

This paper enlightens the RL application on CNC orchestration.

reinforcement-learning Reinforcement Learning (RL) +1