1992 QLearning

• (Watkins & Dayan, 1992) ⇒ Christopher J. C. H. Watkins, and Peter Dayan. (1992). “Technical Note : [math]\displaystyle{ \cal{Q} }[/math]-Learning.” In: Machine Learning Journal, 8(3-4). doi:10.1007/BF00992698

Subject Headings: Q-Learning.

Cited By

• http://scholar.google.com/scholar?q=%221992%22++Technical+Note+%3A+%5Ccal+Q+-Learning
• http://dl.acm.org/citation.cfm?id=139611.139618&preflayout=flat#citedby

Quotes

Abstract

[math]\displaystyle{ \cal{Q} }[/math]-learning (Watkins, 1989) is a simple way for agents to learn how to act optimally in controlled Markovian domains. It amounts to an incremental method for dynamic programming which imposes limited computational demands. It works by successively improving its evaluations of the quality of particular actions at particular states.

This paper presents and proves in detail a convergence theorem for [math]\displaystyle{ \cal Q }[/math]-learning based on that outlined in Watkins (1989). We show that [[[math]\displaystyle{ \cal Q }[/math]-learning converge]]s to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action-values are represented discretely. We also sketch extensions to the cases of non-discounted, but absorbing, Markov environments, and where many [math]\displaystyle{ \cal Q }[/math] values can be changed each iteration, rather than just one.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
1992 QLearning	Christopher J. C. H. Watkins Peter Dayan			Technical Note : \cal Q -Learning				10.1007/BF00992698		1992