haku: @author Eldeib, H. / yhteensä: 1
viite: 1 / 1
« edellinen | seuraava »
| Tekijä: | White, C. Eldeib, H. |
| Otsikko: | Markov decision processes with imprecise transition probabilities |
| Lehti: | Operations Research
1994 : JUL-AUG, VOL. 42:4, p. 739-749 |
| Asiasana: | MARKOV CHAINS DYNAMIC PROGRAMMING OPTIMAL CONTROL THEORY |
| Kieli: | eng |
| Tiivistelmä: | The authors present numerical algorithms and bounds for the infinite horizon, discrete stage, finite state and action Markov decision process with imprecise decision probabilities. The authors assume that the transition probability mass vector for each state and action is described by a finite number of linear inequalities. This model of impresision appears to be well suited for describing statistically determined confidence limits and/or natural language statements of likelihood. |
« edellinen | seuraava »
SCIMA