A Universal Generalization for Temporal-Difference Learning Using Haar Basis Functions.

Susumu Katayama Hajime Kimura Shigenobu Kobayashi

Published in: ICML (2000)

Keyphrases

basis functions
temporal difference learning
function approximation
linear combination
radial basis function
state space
reinforcement learning
fixed point
game playing
evaluation function
temporal difference
reinforcement learning algorithms
markov decision process
decision making
neural network