Poster

Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime

Andrea Agazzi · Jianfeng Lu

Keywords: [ policy gradient ] [ neural networks ] [ entropy regularization ] [ mean-field dynamics ]

[ Abstract ]
[ Paper ]
Tue 4 May 9 a.m. PDT — 11 a.m. PDT

Abstract:

We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate on the training dynamics in the mean-field regime, modeling e.g. the behavior of wide single hidden layer neural networks, when exploration is encouraged through entropy regularization. The dynamics of these models is established as a Wasserstein gradient flow of distributions in parameter space. We further prove global optimality of the fixed points of this dynamics under mild conditions on their initialization.

Chat is not available.