Average cost Markov decision processes under the hypothesis of Doeblin.
Masami KuranoPublished in: Ann. Oper. Res. (1991)
Keyphrases
- average cost
- markov decision processes
- finite state
- state space
- optimal policy
- approximate dynamic programming
- dynamic programming
- transition matrices
- finite horizon
- reinforcement learning
- infinite horizon
- policy iteration
- action space
- reinforcement learning algorithms
- initial state
- markov decision process
- markov decision chains
- action sets
- decision processes
- control policy
- partially observable
- planning under uncertainty
- decision theoretic planning
- risk sensitive
- long run
- finite number
- multistage
- average reward
- learning algorithm
- steady state
- linear programming