Generalized Speedy Q-Learning

John, I and Kamanchi, C and Bhatnagar, S (2020) Generalized Speedy Q-Learning. In: IEEE Control Systems Letters, 4 (3). pp. 524-529.

PDF IEEE_Control_Sys_Letts_4-3_524_2020.pdf - Published Version Restricted to Registered users only Download (773kB) | Request a copy

Abstract

In this letter, we derive a generalization of the Speedy Q-learning (SQL) algorithm that was proposed in the Reinforcement Learning (RL) literature to handle slow convergence of Watkins' Q-learning. In most RL algorithms such as Q-learning, the Bellman equation and the Bellman operator play an important role. It is possible to generalize the Bellman operator using the technique of successive relaxation. We use the generalized Bellman operator to derive a simple and efficient family of algorithms called Generalized Speedy Q-learning (GSQL-w) and analyze its finite time performance. We show that GSQL-w has an improved finite time performance bound compared to SQL for the case when the relaxation parameter w is greater than 1. This improvement is a consequence of the contraction factor of the generalized Bellman operator being less than that of the standard Bellman operator. Numerical experiments are provided to demonstrate the empirical performance of the GSQL-w algorithm. © 2017 IEEE.

Item Type:	Journal Article
Publication:	IEEE Control Systems Letters
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	Copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Dynamic programming; Learning systems; Reinforcement learning; Stochastic control systems; Stochastic systems, Bellman equations; Contraction factor; Empirical performance; Numerical experiments; Performance bounds; Relaxation parameter; Slow convergences; Stochastic optimal control, Learning algorithms
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	01 Jul 2020 11:02
Last Modified:	01 Jul 2020 11:02
URI:	http://eprints.iisc.ac.in/id/eprint/64847

Actions (login required)

View Item