A note on an LQG regulator with Markovian switching and pathwise average cost.
Mohendro Kumar GhoshAri ArapostathisSteven I. MarcusPublished in: IEEE Trans. Autom. Control. (1995)
Keyphrases
- average cost
- optimal control
- linear quadratic
- infinite horizon
- dynamic programming
- risk sensitive
- approximate dynamic programming
- control strategy
- markov decision chains
- inventory models
- reinforcement learning
- finite horizon
- closed loop
- markov decision processes
- steady state
- action sets
- dynamical systems
- control policy
- holding cost
- finite state
- long run
- initial state
- multistage
- special case
- real time
- search algorithm
- linear programming
- optimal policy
- vector valued
- markov decision process
- finite number