Publication

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

Journal of Artificial Intelligence Research


Abstract

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD) reinforcement learning methods can be formally derived, not by starting from their original objective functions, as previously attempted, but rather from a primal-dual saddle-point objective function. We also conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Previous analyses of this class of algorithms use stochastic approximation techniques to prove asymptotic convergence, and do not provide any finite-sample analysis. We also propose an accelerated algorithm, called GTD2-MP, that uses proximal “mirror maps” to yield improved convergence rate. The results of our theoretical analysis imply that the GTD family of algorithms are comparable and may indeed be preferred over existing least squares TD methods for off-policy learning, due to their linear complexity. We provide experimental results showing the improved performance of our accelerated gradient TD methods.

Related Publications

All Publications

A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters

Jungdam Won, Deepak Gopinath, Jessica Hodgins

ACM SIGGRAPH - July 19, 2020

ARCH: Animatable Reconstruction of Clothed Humans

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung

CVPR - June 15, 2020

In Defense of Grid Features for Visual Question Answering

Huaizu Jiang, Ishan Misra, Marcus Rohrbach, Erik Learned-Miller, Xinlei Chen

CVPR - June 14, 2020

Hierarchical Scene Coordinate Classification and Regression for Visual Localization

Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala

CVPR - June 13, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy