Weak conditions for the existence of optimal stationary policies in average Markov decision chains with unbounded costs.
Rolando Cavazos-CadenaPublished in: Kybernetika (1989)
Keyphrases
- average cost
- stationary policies
- markov decision chains
- markov decision processes
- long run
- action sets
- finite state
- finite number
- optimal policy
- total cost
- optimal control
- infinite horizon
- finite horizon
- linear program
- multistage
- linear programming
- markov decision process
- reinforcement learning
- markov chain
- state space
- initial state
- control policy
- risk sensitive
- dynamic programming
- expected cost
- sufficient conditions
- special case