Optimal Stopping Time on Semi-Markov Processes with Finite Horizon.

Fang Chen Xianping Guo Zhong-Wei Liao

Published in: J. Optim. Theory Appl. (2022)

Keyphrases

optimal stopping
finite horizon
optimal policy
infinite horizon
markov decision processes
multistage
markov decision process
dynamic programming
reinforcement learning
state space
non stationary
average cost
sufficient conditions
decision problems