Performance Optimization of Semi-Markov Decision Processes with Discounted-cost Criteria.
Baoqun YinYanjie LiYaping ZhouHongsheng XiPublished in: Eur. J. Control (2008)
Keyphrases
- semi markov decision processes
- average reward
- markov decision processes
- average cost
- optimal policy
- optimization problems
- total cost
- reinforcement learning
- dynamic programming
- state space
- optimization algorithm
- decision making
- finite state
- long run
- expected cost
- policy iteration
- markov chain
- infinite horizon
- cost function