Faster reinforcement learning after pretraining deep networks to predict state dynamics.

Charles W. Anderson Minwoo Lee Daniel L. Elliott

Published in: IJCNN (2015)

Keyphrases

reinforcement learning
state space
complex networks
function approximation
neural network
social networks
control system
dynamical systems
heterogeneous networks
optimal policy
markov decision processes
state variables
finite state machines
temporal difference
cellular automaton