w w w . c s . h m c . e d u / ~ r m c k n i g h /
home
projects
games
photos
nn-seven
antsim
master’s
references
problem statement
approach
results
references
code repository
presentation
credits
Instructions
--> PLAY <--
References
"Temporal Difference Learning and TD-Gammon"
by Gerald Tesauro
"Learning to Play Games From Experience: An Application of Artificial Neural Networks and Temporal Difference Learning"
by Daniel Kenneth Olson (postscript)
rmcknigh@cs.hmc.edu
Sun Jan 15 09:41:13 2006