Multi-objective Influence Diagrams

Radu Marinescu, Abdul Razak, Nic Wilson
Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, PMLR R10:572-581, 2012.

Abstract

We describe multi-objective influence diagrams, based on a set of p objectives, where utility values are vectors in Rp, and are typically only partially ordered. These can still be solved by a variable elimination algorithm, leading to a set of maximal values of expected utility. If the Pareto ordering is used this set can often be prohibitively large. We consider approximate representations of the Pareto set based on e-coverings, allowing much larger problems to be solved. In addition, we define a method for incorporating user tradeoffs, which also greatly improves the efficiency.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR10-marinescu12a, title = {Multi-objective Influence Diagrams}, author = {Marinescu, Radu and Razak, Abdul and Wilson, Nic}, booktitle = {Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence}, pages = {572--581}, year = {2012}, editor = {de Freitas, Nando and Murphy, Kevin}, volume = {R10}, series = {Proceedings of Machine Learning Research}, month = {14--18 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r10/main/assets/marinescu12a/marinescu12a.pdf}, url = {https://proceedings.mlr.press/r10/marinescu12a.html}, abstract = {We describe multi-objective influence diagrams, based on a set of p objectives, where utility values are vectors in Rp, and are typically only partially ordered. These can still be solved by a variable elimination algorithm, leading to a set of maximal values of expected utility. If the Pareto ordering is used this set can often be prohibitively large. We consider approximate representations of the Pareto set based on e-coverings, allowing much larger problems to be solved. In addition, we define a method for incorporating user tradeoffs, which also greatly improves the efficiency.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Multi-objective Influence Diagrams %A Radu Marinescu %A Abdul Razak %A Nic Wilson %B Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2012 %E Nando de Freitas %E Kevin Murphy %F pmlr-vR10-marinescu12a %I PMLR %P 572--581 %U https://proceedings.mlr.press/r10/marinescu12a.html %V R10 %X We describe multi-objective influence diagrams, based on a set of p objectives, where utility values are vectors in Rp, and are typically only partially ordered. These can still be solved by a variable elimination algorithm, leading to a set of maximal values of expected utility. If the Pareto ordering is used this set can often be prohibitively large. We consider approximate representations of the Pareto set based on e-coverings, allowing much larger problems to be solved. In addition, we define a method for incorporating user tradeoffs, which also greatly improves the efficiency. %Z Reissued by PMLR on 04 October 2026.
APA
Marinescu, R., Razak, A. & Wilson, N.. (2012). Multi-objective Influence Diagrams. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R10:572-581 Available from https://proceedings.mlr.press/r10/marinescu12a.html. Reissued by PMLR on 04 October 2026.

Related Material