Do evaluation functions really improve Monte-Carlo tree search?

Kiminori Matsuzaki Naoki Kitamura

Published in: J. Int. Comput. Games Assoc. (2018)

Keyphrases

evaluation function
monte carlo tree search
monte carlo search
temporal difference
heuristic function
bayesian reinforcement learning
temporal difference learning
game tree
two player games
linear programming
monte carlo
statistically significant
expected outcome