ML Anthology

Robust Planning with (L)RTDP

Olivier Buffet, Douglas Aberdeen
IJCAI 2005 pp. 1214-1219
/ijcai/2005/buffet2005ijcai-robust/

Abstract

Stochastic Shortest Path problems (SSPs), a sub-class 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. 1

PDF Semantic Scholar

Cite

Text

Buffet and Aberdeen. "Robust Planning with (L)RTDP." International Joint Conference on Artificial Intelligence, 2005.

Markdown

[Buffet and Aberdeen. "Robust Planning with (L)RTDP." International Joint Conference on Artificial Intelligence, 2005.](https://mlanthology.org/ijcai/2005/buffet2005ijcai-robust/)

BibTeX

@inproceedings{buffet2005ijcai-robust,
  title     = {{Robust Planning with (L)RTDP}},
  author    = {Buffet, Olivier and Aberdeen, Douglas},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2005},
  pages     = {1214-1219},
  url       = {https://mlanthology.org/ijcai/2005/buffet2005ijcai-robust/}
}