Constrained continuous-time Markov decision processes with average criteria
β Scribed by Lanlan Zhang; Xianping Guo
- Publisher
- Springer
- Year
- 2007
- Tongue
- English
- Weight
- 268 KB
- Volume
- 67
- Category
- Article
- ISSN
- 0340-9422
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
This brief paper presents a policy improvement method for constrained Markov decision processes (MDPs) with average cost criterion under an ergodicity assumption, extending Howard's policy improvement for MDPs. The improvement method induces a policy iteration-type algorithm that converges to a loca
Time Markov decision processes with countable states and actions continuous are discussed with the criterion of discounted moment optimality. They are transformed into a sequence of discrete time Markov decision processes with the criterion of discounted expected total rewards.