On the Well-Behavedness of Important Attribute Evaluation Functions.

Tapio Elomaa Juho Rousu

Published in: SCAI (1997)

Keyphrases

evaluation function
temporal difference
heuristic function
two player games
attribute values
alpha beta
branching factor
td learning
game tree
temporal difference learning
optimality criterion
objective function
markov chain
monte carlo search
expected outcome