@Article{	  watkins92a,
  author =	 {Christopher J. C. H. Watkins and Peter Dayan},
  title =	 {Q-Learning},
  googleid =	 {3Y3Leyb3Hs8J:scholar.google.com/},
  journal =	 {Machine Learning},
  volume =	 8,
  number =	 {3-4},
  pages =	 {279--292},
  year =	 1992,
  abstract =	 {Q-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 Q,-learning based on that outlined in Watkins
                  (1989). We show that Q-learning converges 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 Q values can be changed each
                  iteration, rather than just one.},
  keywords =     {ai reinforcement learning},
  url =		 {http://jmvidal.cse.sc.edu/library/watkins92a.pdf},
  doi =		 {10.1023/A:1022676722315},
  cluster = 	 {14924637959810158045}
}