Monte Carlo tree search with temporal-difference learning for general video game playing.

Ercument Ilhan A. Sima Etaner-Uyar

Published in: CIG (2017)

Keyphrases

temporal difference learning
game playing
monte carlo tree search
game tree
fixed point
video games
function approximation
reinforcement learning
evaluation function
temporal difference
monte carlo
multimedia
attitudes toward
dynamic environments
sufficient conditions
cost function
search algorithm