Zero-Order Optimization Methods with Applications to Reinforcement Learning

9/19/19 | 4:15pm | E51-335
Reception to follow.





Jorge Nocedal

Northwestern University

Abstract: We consider the problem of minimizing a noisy objective function using only function values. We first review the main approaches in the literature and then focus on two strategies that aim at estimating gradients. One is based on Gaussian smoothing, and we illustrate its performance on some reinforcement learning tasks. The second strategy makes use of a noise estimation procedure due to Hamming, and we test it on general black box optimization problems. 

Bio: Jorge Nocedal is the Walter P. Murphy Professor in the Department of Industrial Engineering and Management Sciences at Northwestern University. His research is in optimization, both deterministic and stochastic, and with emphasis on very large-scale problems. He is a SIAM Fellow, was awarded the 2012 George B. Dantzig Prize, and the 2017 Von Neumann Theory Prize for contributions to theory and algorithms of nonlinear optimization.

Event Time: 

2019 - 16:15