The Steady-State Control Problem for Markov Decision Processes.
S. AkshayNathalie BertrandSerge HaddadLoïc HélouëtPublished in: QEST (2013)
Keyphrases
- steady state
- markov decision processes
- markov chain
- operating conditions
- state space
- finite state
- reinforcement learning
- optimal policy
- dynamic programming
- transition matrices
- policy iteration
- explicit expressions
- product form
- decision theoretic planning
- steady states
- finite horizon
- heavy traffic
- partially observable
- infinite horizon
- average cost
- control problems
- optimal control
- control strategy
- arrival rate
- queueing networks
- reward function
- action space
- average reward
- control system
- state dependent
- multistage
- machine learning