Tuning evaluation functions by maximizing concordance.

Dave Gomboc Michael Buro T. Anthony Marsland

Published in: Theor. Comput. Sci. (2005)

Keyphrases

evaluation function
temporal difference
temporal difference learning
td learning
branching factor
two player games
monte carlo search
heuristic function
expected outcome
image segmentation
markov chain
iterative deepening
monte carlo tree search