Distribution over Beliefs for Memory Bounded Dec-POMDP Planning

Gabriel Corona, François Charpillet
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:143-150, 2010.

Abstract

We propose a new point-based method for approximate planning in Dec-POMDP which outperforms the state-of-the-art approaches in terms of solution quality. It uses a heuris- tic estimation of the prior probability of be- liefs to choose a bounded number of policy trees: this choice is formulated as a combina- torial optimisation problem minimising the error induced by pruning.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-corona10a, title = {Distribution over Beliefs for Memory Bounded Dec-{POMDP} Planning}, author = {Corona, Gabriel and Charpillet, Fran{\c{c}}ois}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {143--150}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/corona10a/corona10a.pdf}, url = {https://proceedings.mlr.press/r8/corona10a.html}, abstract = {We propose a new point-based method for approximate planning in Dec-POMDP which outperforms the state-of-the-art approaches in terms of solution quality. It uses a heuris- tic estimation of the prior probability of be- liefs to choose a bounded number of policy trees: this choice is formulated as a combina- torial optimisation problem minimising the error induced by pruning.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Distribution over Beliefs for Memory Bounded Dec-POMDP Planning %A Gabriel Corona %A François Charpillet %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-corona10a %I PMLR %P 143--150 %U https://proceedings.mlr.press/r8/corona10a.html %V R8 %X We propose a new point-based method for approximate planning in Dec-POMDP which outperforms the state-of-the-art approaches in terms of solution quality. It uses a heuris- tic estimation of the prior probability of be- liefs to choose a bounded number of policy trees: this choice is formulated as a combina- torial optimisation problem minimising the error induced by pruning. %Z Reissued by PMLR on 04 October 2026.
APA
Corona, G. & Charpillet, F.. (2010). Distribution over Beliefs for Memory Bounded Dec-POMDP Planning. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:143-150 Available from https://proceedings.mlr.press/r8/corona10a.html. Reissued by PMLR on 04 October 2026.

Related Material