Testing general game players against a Simplified Boardgames player using temporal-difference learning.

Jakub Kowalski Andrzej Kisielewicz

Published in: CEC (2015)

Keyphrases

temporal difference learning
game players
game playing
game play
function approximation
reinforcement learning
evaluation function
fixed point
neural network
machine learning
software engineering
statistically significant
dynamical systems
video games
temporal difference
online game