Application Of Markov Decision Processes To The Frequency Assignment Problem.

Jean-Yves Greff Lhassane Idoumghar René Schott

Published in: Appl. Artif. Intell. (2004)

Keyphrases

markov decision processes
state space
reinforcement learning
optimal policy
finite state
transition matrices
dynamic programming
planning under uncertainty
policy iteration
action space
average reward
reinforcement learning algorithms
reachability analysis
average cost
finite horizon
risk sensitive
markov chain