Self-Play and Using an Expert to Learn to Play Backgammon with Temporal Difference Learning.

Marco A. Wiering

Published in: J. Intell. Learn. Syst. Appl. (2010)

Keyphrases

temporal difference learning
game playing
fixed point
evaluation function
approximate value iteration
function approximation
temporal difference
reinforcement learning
function approximators
pairwise
graphical models
human players