Login / Signup
Coevolution versus self-play temporal difference learning for acquiring position evaluation in small-board go.
Thomas Philip Runarsson
Simon M. Lucas
Published in:
IEEE Trans. Evol. Comput. (2005)
Keyphrases
</>
temporal difference learning
game playing
function approximation
fixed point
evaluation function
reinforcement learning
approximate value iteration
temporal difference
reinforcement learning algorithms
markov decision process
neural network
machine learning
active learning
attitudes toward
policy iteration