Automatic abstraction in reinforcement learning using data mining techniques.

Ghorban Kheradmandian Mohammad Rahmati

Published in: Robotics Auton. Syst. (2009)

Keyphrases

reinforcement learning
function approximation
state abstraction
data driven
semi automatic
learning algorithm
fully automatic
model free
reinforcement learning algorithms
data sets
multi agent
least squares
markov decision processes
temporal difference
learning capabilities