Deterministic POMDPs Revisited

Blai Bonet
Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, PMLR R7:51-58, 2009.

Abstract

We study a subclass of POMDPs, called Deterministic POMDPs, that is characterized by deterministic actions and observations. These models do not provide the same generality of POMDPs yet they capture a number of interesting and challenging problems, and permit more efficient algorithms. Indeed, some of the recent work in planning is built around such assumptions mainly by the quest of amenable models more expressive than the classical deterministic models. We provide results about the fundamental properties of Deterministic POMDPs, their relation with AND/OR search problems and algorithms, and their computational complexity.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR7-bonet09a, title = {Deterministic POMDPs Revisited}, author = {Bonet, Blai}, booktitle = {Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence}, pages = {51--58}, year = {2009}, editor = {Bilmes, Jeff and Ng, Andrew Y.}, volume = {R7}, series = {Proceedings of Machine Learning Research}, month = {18--21 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r7/main/assets/bonet09a/bonet09a.pdf}, url = {https://proceedings.mlr.press/r7/bonet09a.html}, abstract = {We study a subclass of POMDPs, called Deterministic POMDPs, that is characterized by deterministic actions and observations. These models do not provide the same generality of POMDPs yet they capture a number of interesting and challenging problems, and permit more efficient algorithms. Indeed, some of the recent work in planning is built around such assumptions mainly by the quest of amenable models more expressive than the classical deterministic models. We provide results about the fundamental properties of Deterministic POMDPs, their relation with AND/OR search problems and algorithms, and their computational complexity.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Deterministic POMDPs Revisited %A Blai Bonet %B Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2009 %E Jeff Bilmes %E Andrew Y. Ng %F pmlr-vR7-bonet09a %I PMLR %P 51--58 %U https://proceedings.mlr.press/r7/bonet09a.html %V R7 %X We study a subclass of POMDPs, called Deterministic POMDPs, that is characterized by deterministic actions and observations. These models do not provide the same generality of POMDPs yet they capture a number of interesting and challenging problems, and permit more efficient algorithms. Indeed, some of the recent work in planning is built around such assumptions mainly by the quest of amenable models more expressive than the classical deterministic models. We provide results about the fundamental properties of Deterministic POMDPs, their relation with AND/OR search problems and algorithms, and their computational complexity. %Z Reissued by PMLR on 04 October 2026.
APA
Bonet, B.. (2009). Deterministic POMDPs Revisited. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R7:51-58 Available from https://proceedings.mlr.press/r7/bonet09a.html. Reissued by PMLR on 04 October 2026.

Related Material