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 ….
‘store’ the Q-values. In our experiments we use neural networks as a function
approximator, and therefore we consider this … method in more detail. We as-
sume that the reader has basic knowledge about feedforward neural networks.
For an introduction …