## 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
โฆ LIBER โฆ
2. Decision and control : Comparison of convergent and divergent Markov decision processes
โ Scribed by K.J. Sarma
- Publisher
- Elsevier Science
- Year
- 1984
- Tongue
- English
- Weight
- 106 KB
- Volume
- 18
- Category
- Article
- ISSN
- 0304-4149
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
Bounding reward measures of Markov model
โ
Peter Buchholz
๐
Article
๐
2011
๐
John Wiley and Sons
๐
English
โ 388 KB
On the General Utility of Discounted Mar
โ
Y. Kadota; M. Kurano; M. Yasuda
๐
Article
๐
1998
๐
John Wiley and Sons
๐
English
โ 182 KB
Vector-valued Markov decision processes
โ
Kazuyoshi Wakuta
๐
Article
๐
1995
๐
Elsevier Science
๐
English
โ 496 KB
Utility, probabilistic constraints, mean
โ
D. J. White
๐
Article
๐
1987
๐
Springer
๐
German
โ 847 KB
Suboptimal policy determination for larg
โ
J. L. Popyack; C. C. White
๐
Article
๐
1985
๐
Springer
๐
English
โ 793 KB
Outcome effects: The impact of decision
โ
Hun-Tong Tan; Marlys Gascho Lipe
๐
Article
๐
1997
๐
John Wiley and Sons
๐
English
โ 159 KB
๐ 2 views
An `outcome eect' refers to the phenomenon whereby performance evaluations of decision makers are aected by the outcomes of those decisions. Although some consider such an eect to be a judgmental error, judgment by outcomes may not be dysfunctional when the evaluator does not know how the decision m