Sign in
Evolving small-board Go players using coevolutionary temporal difference learning with archives.
Krzysztof Krawiec
Wojciech Jaskowski
Marcin Grzegorz Szubert
Published in:
Int. J. Appl. Math. Comput. Sci. (2011)
Keyphrases
</>
temporal difference learning
game playing
function approximation
board game
fixed point
reinforcement learning
approximate value iteration
evaluation function
temporal difference
reinforcement learning algorithms
markov decision process
linear combination
monte carlo