Learning n-tuple networks for othello by coevolutionary gradient search.

Krzysztof Krawiec Marcin Grzegorz Szubert

Published in: GECCO (2011)

Keyphrases

temporal difference learning
learning algorithm
learning process
search algorithm
game playing
board game
reinforcement learning
evaluation function
learning scenarios
neural network
search space
supervised learning
search strategies
temporal difference
game tree