Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be ‘close’ to one another, is iteratively solved. Nevertheless, TRPO has been considered a heuristic algorithm inspired by Conservative Policy Iteration (CPI). We show that the adaptive scaling mechanism used in TRPO is in fact the natural “RL version” of traditional trust-region methods from convex analysis. We first analyze TRPO in the planning setting, in which we have access to the model and the entire state space. Then, we consider sample-based TRPO and establish Õ(1/√N) convergence rate to the global optimum. Importantly, the adaptive scaling mechanism allows us to analyze TRPO in regularized MDPs for which we prove fast rates of Õ(1/N), much like results in convex optimization. This is the first result in RL of better rates when regularizing the instantaneous cost or reward.
Published Date: 2020-06-02
Registration: ISSN 2374-3468 (Online) ISSN 2159-5399 (Print) ISBN 978-1-57735-835-0 (10 issue set)
Copyright: Published by AAAI Press, Palo Alto, California USA Copyright © 2020, Association for the Advancement of Artificial Intelligence All Rights Reserved