pith. machine review for the scientific record. sign in

arxiv: 1811.11214 · v5 · submitted 2018-11-27 · 💻 cs.LG · stat.ML

Recognition: unknown

Understanding the impact of entropy on policy optimization

Authors on Pith no claims yet
classification 💻 cs.LG stat.ML
keywords optimizationpolicyentropylandscapefunctionlearningunderstandingaccess
0
0 comments X
read the original abstract

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbing the loss function. We first show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. Then, we qualitatively show that in some environments, a policy with higher entropy can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This paper presents new tools for understanding the optimization landscape, shows that policy entropy serves as a regularizer, and highlights the challenge of designing general-purpose policy optimization algorithms.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.