Login / Signup
Containment of socially optimal policies in multiple-facility Markovian queueing systems Open.
Rob Shone
Vincent A. Knight
Paul R. Harper
Janet E. Williams
John Minty
Published in:
J. Oper. Res. Soc. (2016)
Keyphrases
</>
optimal policy
markov decision processes
reinforcement learning
state space
search algorithm
dynamic programming
long run
decision problems
infinite horizon
data mining
sufficient conditions
finite state
control policies
average reward reinforcement learning
serial inventory systems