Optimal Policy for a Class of Compartmental Models.

Aye Thanda Pyke Tin Koichiro Ochimizu

Published in: ICITA (1) (2005)

Keyphrases

optimal policy
stochastic inventory control
markov decision processes
finite horizon
reinforcement learning
state space
long run
state dependent
control policies
decision problems
dynamic programming
probabilistic model
machine learning
sufficient conditions
infinite horizon