Publications [#353378] of Andrea Agazzi

Papers Published

1. Agazzi, A; Lu, J, Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime, vol. abs/2010.11858 (October, 2020)
   (last updated on 2022/05/25)

   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.