Markov decision process in the problem of dynamic pricing policy.

Yu. A. Chizhov Arkady N. Borisov

Published in: Autom. Control. Comput. Sci. (2011)

Keyphrases

markov decision process
optimal policy
reinforcement learning
state space
finite horizon
infinite horizon
search algorithm
dynamic environments
markov decision processes
computational complexity
em algorithm
multistage
initial state
policy iteration
transition matrices