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

Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective

2019-01-31
Anirudh Vemula, Wen Sun, J. Andrew Bagnell

Abstract

Black-box optimizers that explore in parameter space have often been shown to outperform more sophisticated action space exploration methods developed specifically for the reinforcement learning problem. We examine these black-box methods closely to identify situations in which they are worse than action space exploration methods and those in which they are superior. Through simple theoretical analyses, we prove that complexity of exploration in parameter space depends on the dimensionality of parameter space, while complexity of exploration in action space depends on both the dimensionality of action space and horizon length. This is also demonstrated empirically by comparing simple exploration methods on several model problems, including Contextual Bandit, Linear Regression and Reinforcement Learning in continuous control.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.11503

PDF

http://arxiv.org/pdf/1901.11503


Similar Posts

Comments