papers AI Learner
The Github is limit! Click to go to the new site.

Boosting Trust Region Policy Optimization by Normalizing Flows Policy

2019-01-29
Yunhao Tang, Shipra Agrawal

Abstract

We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the ‘center’ of the previous policy iterate, which potentially enables better exploration and helps avoid bad local optima. Through extensive comparisons, we show that the normalizing flows policy significantly improves upon baseline architectures especially on high-dimensional tasks with complex dynamics.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1809.10326

PDF

http://arxiv.org/pdf/1809.10326


Similar Posts

Comments