Online policy iteration algorithm for semi-Markov switching state-space control processes.

Qi Jiang Hongsheng Xi Bao-Qin Yin

Published in: CDC (2009)

Keyphrases

semi markov
state space
markov decision processes
policy iteration algorithm
control system
reinforcement learning
heuristic search
dynamic programming
conditional random fields
optimal control
optimal policy
control problems
markov decision process