Skip to Main content Skip to Navigation
Reports

Planning with Robust (L)RTDP

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.
Document type :
Reports
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/inria-00509352
Contributor : Olivier Buffet Connect in order to contact the contributor
Submitted on : Wednesday, August 11, 2010 - 6:05:30 PM
Last modification on : Friday, September 16, 2016 - 3:06:09 PM
Long-term archiving on: : Thursday, December 1, 2016 - 11:49:34 AM

File

rlrtdp.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00509352, version 1

Collections

Citation

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

Share

Metrics

Record views

61

Files downloads

102