Planning with Robust (L)RTDP - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2004

Planning with Robust (L)RTDP

Olivier Buffet
Douglas Aberdeen
  • Function : Author
  • PersonId : 854488

Abstract

Stochastic Shortest Path problems (SSPs), a subclass of Markov Decision Problems (MDPs), can be efficiently dealt with using Real-Time Dynamic Programming (RTDP). Yet, MDP models are often uncertain (obtained through statistics or guessing). The usual approach is robust planning: searching for the best policy under the worst model. This paper shows how RTDP can be made robust in the common case where transition probabilities are known to lie in a given interval.
Fichier principal
Vignette du fichier
rlrtdp.pdf (413.49 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00509352 , version 1 (11-08-2010)

Identifiers

  • HAL Id : inria-00509352 , version 1

Cite

Olivier Buffet, Douglas Aberdeen. Planning with Robust (L)RTDP. [Research Report] 2004, pp.21. ⟨inria-00509352⟩
73 View
109 Download

Share

Gmail Facebook X LinkedIn More