Login / Signup
On a staged successive approximation procedure for approximate dynamic programming solutions to board game playing.
Eiji Mizutani
Published in:
IEEM (2015)
Keyphrases
</>
game playing
approximate dynamic programming
tic tac toe
successive approximation
board game
linear program
general game playing
dynamic programming
reinforcement learning
video games
step size
game play
computer games
markov chain
average cost
rate distortion
multistage
multiresolution