Characterizing EVOI-Sufficient k-Response Query Sets in Decision Problems

Robert Cohn, Satinder Singh, Edmund Durfee
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:131-139, 2014.

Abstract

In finite decision problems where an agent can query its human user to obtain information about its environment before acting, a query’s usefulness is in terms of its Expected Value of Information (EVOI). The usefulness of a query set is similarly measured in terms of the EVOI of the queries it contains. When the only constraint on what queries can be asked is that they have exactly k possible responses (with k \ge 2), we show that the set of k-response decision queries (which ask the user to select his/her preferred decision given a choice of k decisions) is EVOI-Sufficient, meaning that no single k-response query can have higher EVOI than the best single k-response decision query for any decision problem. When multiple queries can be asked before acting, we provide a negative result that shows the set of depth-n query trees constructed from k-response decision queries is not EVOI-Sufficient. However, we also provide a positive result that the set of depth-n query trees constructed from k-response decision-set queries, which ask the user to select from among k sets of decisions as to which set contains the best decision, is EVOI-Sufficient. We conclude with a discussion and analysis of algorithms that draws on a connection to other recent work on decision-theoretic knowledge elicitation.

Cite this Paper


BibTeX
@InProceedings{pmlr-v33-cohn14, title = {{Characterizing EVOI-Sufficient k-Response Query Sets in Decision Problems}}, author = {Cohn, Robert and Singh, Satinder and Durfee, Edmund}, booktitle = {Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics}, pages = {131--139}, year = {2014}, editor = {Kaski, Samuel and Corander, Jukka}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/cohn14.pdf}, url = {https://proceedings.mlr.press/v33/cohn14.html}, abstract = {In finite decision problems where an agent can query its human user to obtain information about its environment before acting, a query’s usefulness is in terms of its Expected Value of Information (EVOI). The usefulness of a query set is similarly measured in terms of the EVOI of the queries it contains. When the only constraint on what queries can be asked is that they have exactly k possible responses (with k \ge 2), we show that the set of k-response decision queries (which ask the user to select his/her preferred decision given a choice of k decisions) is EVOI-Sufficient, meaning that no single k-response query can have higher EVOI than the best single k-response decision query for any decision problem. When multiple queries can be asked before acting, we provide a negative result that shows the set of depth-n query trees constructed from k-response decision queries is not EVOI-Sufficient. However, we also provide a positive result that the set of depth-n query trees constructed from k-response decision-set queries, which ask the user to select from among k sets of decisions as to which set contains the best decision, is EVOI-Sufficient. We conclude with a discussion and analysis of algorithms that draws on a connection to other recent work on decision-theoretic knowledge elicitation.} }
Endnote
%0 Conference Paper %T Characterizing EVOI-Sufficient k-Response Query Sets in Decision Problems %A Robert Cohn %A Satinder Singh %A Edmund Durfee %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-cohn14 %I PMLR %P 131--139 %U https://proceedings.mlr.press/v33/cohn14.html %V 33 %X In finite decision problems where an agent can query its human user to obtain information about its environment before acting, a query’s usefulness is in terms of its Expected Value of Information (EVOI). The usefulness of a query set is similarly measured in terms of the EVOI of the queries it contains. When the only constraint on what queries can be asked is that they have exactly k possible responses (with k \ge 2), we show that the set of k-response decision queries (which ask the user to select his/her preferred decision given a choice of k decisions) is EVOI-Sufficient, meaning that no single k-response query can have higher EVOI than the best single k-response decision query for any decision problem. When multiple queries can be asked before acting, we provide a negative result that shows the set of depth-n query trees constructed from k-response decision queries is not EVOI-Sufficient. However, we also provide a positive result that the set of depth-n query trees constructed from k-response decision-set queries, which ask the user to select from among k sets of decisions as to which set contains the best decision, is EVOI-Sufficient. We conclude with a discussion and analysis of algorithms that draws on a connection to other recent work on decision-theoretic knowledge elicitation.
RIS
TY - CPAPER TI - Characterizing EVOI-Sufficient k-Response Query Sets in Decision Problems AU - Robert Cohn AU - Satinder Singh AU - Edmund Durfee BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-cohn14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 33 SP - 131 EP - 139 L1 - http://proceedings.mlr.press/v33/cohn14.pdf UR - https://proceedings.mlr.press/v33/cohn14.html AB - In finite decision problems where an agent can query its human user to obtain information about its environment before acting, a query’s usefulness is in terms of its Expected Value of Information (EVOI). The usefulness of a query set is similarly measured in terms of the EVOI of the queries it contains. When the only constraint on what queries can be asked is that they have exactly k possible responses (with k \ge 2), we show that the set of k-response decision queries (which ask the user to select his/her preferred decision given a choice of k decisions) is EVOI-Sufficient, meaning that no single k-response query can have higher EVOI than the best single k-response decision query for any decision problem. When multiple queries can be asked before acting, we provide a negative result that shows the set of depth-n query trees constructed from k-response decision queries is not EVOI-Sufficient. However, we also provide a positive result that the set of depth-n query trees constructed from k-response decision-set queries, which ask the user to select from among k sets of decisions as to which set contains the best decision, is EVOI-Sufficient. We conclude with a discussion and analysis of algorithms that draws on a connection to other recent work on decision-theoretic knowledge elicitation. ER -
APA
Cohn, R., Singh, S. & Durfee, E.. (2014). Characterizing EVOI-Sufficient k-Response Query Sets in Decision Problems. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 33:131-139 Available from https://proceedings.mlr.press/v33/cohn14.html.

Related Material