αβ-based play-outs in Monte-Carlo Tree Search.

Mark H. M. Winands Yngvi Björnsson

Published in: CIG (2011)

Keyphrases

monte carlo tree search
monte carlo
tree search algorithm
evaluation function
bayesian reinforcement learning
game tree
alpha beta search
game playing
neural network
machine learning
lower bound
markov chain
temporal difference
temporal difference learning
reinforcement learning methods