Multiscale Q-learning with linear function approximation

Bhatnagar, Shalabh; Lakshmanan, K.

doi:10.1007/s10626-015-0216-z

Cited by 4 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Double Q-learning [7] and Speedy Q-learning [4] use two estimates of the Qfunction, for addressing the issues of over-estimation and slow convergence, respectively. A multi-timescale version of the Qlearning algorithm is presented in [8] and its convergence shown using a differential inclusions based analysis. More recently, the Zap Q-learning algorithm was introduced [9], which is a matrix-gain algorithm designed to optimize the asymptotic variance.…”

Section: A Related Workmentioning

confidence: 99%

Generalized Speedy Q-Learning

John

Kamanchi

Bhatnagar

2020

IEEE Control Syst. Lett.

Self Cite

View full text Add to dashboard Cite

In this paper, 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 Qlearning, 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 GSQLw 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 GSQLw algorithm.

show abstract

Section: A Related Workmentioning

confidence: 99%