Mathematics of Deep Learning
Spring 2020

Constrained optimization and ADMM

Motivation

Guided policy search formulates its objective as a constrained optimization, minimizing the cost of its expert trajectories while guaranteeing that, at convergence, the expert trajectories and the neural network policy become identical. After this week you should understand the problem of constrained optimization and the specific technique, ADMM, used by GPS.

Topics

Required reading

Optional reading

Questions