Optimal policies for production-clearing systems under continuous-review.

Remco Germs Nicky D. van Foreest Onur A. Kilic

Published in: Eur. J. Oper. Res. (2016)

Keyphrases

optimal policy
reinforcement learning
markov decision processes
decision problems
dynamic programming
state space
finite state
finite horizon
dynamic programming algorithms
computational complexity
sufficient conditions
long run
action space
average reward