A Curling Agent Based on the Monte-Carlo Tree Search Considering the Similarity of the Best Action Among Similar States.

Katsuki Ohto Tetsuro Tanaka

Published in: ACG (2017)

Keyphrases

monte carlo tree search
monte carlo
evaluation function
initial state
bayesian reinforcement learning
multi agent
action selection
tree search algorithm
alpha beta search
e learning
multi agent systems
temporal difference