Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs.
Linn I. SennottPublished in: Oper. Res. (1989)
Keyphrases
- average cost
- markov decision processes
- stationary policies
- action sets
- finite state
- optimal policy
- state space
- long run
- finite horizon
- dynamic programming
- reinforcement learning
- infinite horizon
- policy iteration
- risk sensitive
- finite number
- total reward
- optimal control
- markov decision process
- total cost
- average reward
- decision processes
- planning under uncertainty
- markov decision problems
- reinforcement learning algorithms
- initial state
- control policy
- linear program
- multistage
- linear programming