Wezel, M.C. van; Eck, N.J.P. van - Erasmus University Rotterdam, Econometric Institute - 2005
Learning, Markov Decision Processes, Dynamic Programming, Neural
Networks, Game Playing, Gaming, Othello.
1 Introduction
Many … exist a number of algorithms that nd the optimal policy, col-
lectively known as dynamic programming methods. A problem … with dynamic
programming methods is that they are unable to deal with problems in which
the number of possible states is …