Improving reinforcement learning by using sequence trees

Author: Girgin Sertan  

Publisher: Springer Publishing Company

ISSN: 0885-6125

Source: Machine Learning, Vol.81, Iss.3, 2010-12, pp. : 283-331

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

This paper proposes a novel approach to discover options in the form of stochastic conditionally terminating sequences; it shows how such sequences can be integrated into the reinforcement learning framework to improve the learning performance. The method utilizes stored histories of possible optimal policies and constructs a specialized tree structure during the learning process. The constructed tree facilitates the process of identifying frequently used action sequences together with states that are visited during the execution of such sequences. The tree is constantly updated and used to implicitly run corresponding options. The effectiveness of the method is demonstrated empirically by conducting extensive experiments on various domains with different properties.