Exploiting Additive Structure in Factored MDPs for Reinforcement Learning.

Thomas Degris Olivier Sigaud Pierre-Henri Wuillemin

Published in: EWRL (2008)

Keyphrases

factored mdps
reinforcement learning
markov decision processes
state space
approximate dynamic programming
context specific
learning algorithm
multi agent
least squares
random walk
real valued
function approximation
policy iteration