We consider a Markov decision process with an uncountable state space and multiple rewards. For each policy, its performance is evaluated by a vector of total expected rewards. Under the standard continuity assumptions and the additional assumption that all initial and transition probabilities are n
β¦ LIBER β¦
Weighted reward criteria in Competitive Markov Decision Processes
β Scribed by J. A. Filar; O. J. Vrieze
- Publisher
- Springer
- Year
- 1992
- Tongue
- English
- Weight
- 689 KB
- Volume
- 36
- Category
- Article
- ISSN
- 0340-9422
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Multiple Objective Nonatomic Markov Deci
β
Eugene A. Feinberg; Aleksey B. Piunovskiy
π
Article
π
2000
π
Elsevier Science
π
English
β 228 KB
Markov Decision Processes: Discounted Ex
β
D.J. White
π
Article
π
1993
π
Elsevier Science
π
English
β 275 KB
Weighted Markov decision processes with
β
Ke Liu; Jerzy A. Filar
π
Article
π
2001
π
Springer
π
English
β 149 KB
Reward revision and the average reward m
β
C. C. White; W. T. Scherer
π
Article
π
1987
π
Springer
π
German
β 578 KB
Bounding reward measures of Markov model
β
Peter Buchholz
π
Article
π
2011
π
John Wiley and Sons
π
English
β 388 KB
## SUMMARY For a Markov reward process, where upper and lower bounds for the transition rates and rewards are known, a new approach to bound the expected reward is presented. Based on a previous paper where sharp bounds have been defined for the problem, but only an inefficient and unstable algorit
A multicriteria competitive Markov decis
β
A. M. RodrΔ±Β΄guez-ChΔ±Β΄a; J. Puerto; F. R. FernΓ‘ndez
π
Article
π
2002
π
Springer
π
English
β 114 KB