Development of a reinforcement learning system to play Othello.

Kazuteru Miyazaki Sougo Tsuboi Shigenobu Kobayashi

Published in: Artif. Life Robotics (2004)

Keyphrases

temporal difference learning
game playing
reinforcement learning
temporal difference
evaluation function
minimax search
board game
function approximation
game tree
state space
fixed point
software engineering
markov decision processes
game tree search
world class
design principles
action selection