Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory

Philipp Geiger, Michel Besserve, Justus Winkelmann, Claudius Proissl, Bernhard Schölkopf
Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, PMLR 115:207-216, 2020.

Abstract

We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.), to support coordination between them, and increase efficiency of such collective systems. Key questions are: (1) when and how much can (accurate) predictions help for coordination, and (2) which assistant algorithms reach optimal predictions? First we lay conceptual ground for this setting where user preferences are a priori unknown and predictions influence outcomes. Addressing (1), we establish conditions under which self-fulfilling prophecies, i.e., “perfect” (probabilistic) predictions of what will happen, solve the coordination problem in the gametheoretic sense of selecting a Bayesian Nash equilibrium (BNE). Next we prove that such prophecies exist even in large-scale settings where only aggregated statistics about users are available. This entails a new (nonatomic) BNE existence result. Addressing (2), we propose two assistant algorithms that sequentially learn from users’ reactions, together with optimality/ convergence guarantees. We validate one of them in a large real-world experiment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v115-geiger20a, title = {Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory}, author = {Geiger, Philipp and Besserve, Michel and Winkelmann, Justus and Proissl, Claudius and Sch{\"{o}}lkopf, Bernhard}, booktitle = {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference}, pages = {207--216}, year = {2020}, editor = {Adams, Ryan P. and Gogate, Vibhav}, volume = {115}, series = {Proceedings of Machine Learning Research}, month = {22--25 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v115/geiger20a/geiger20a.pdf}, url = {https://proceedings.mlr.press/v115/geiger20a.html}, abstract = {We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.), to support coordination between them, and increase efficiency of such collective systems. Key questions are: (1) when and how much can (accurate) predictions help for coordination, and (2) which assistant algorithms reach optimal predictions? First we lay conceptual ground for this setting where user preferences are a priori unknown and predictions influence outcomes. Addressing (1), we establish conditions under which self-fulfilling prophecies, i.e., “perfect” (probabilistic) predictions of what will happen, solve the coordination problem in the gametheoretic sense of selecting a Bayesian Nash equilibrium (BNE). Next we prove that such prophecies exist even in large-scale settings where only aggregated statistics about users are available. This entails a new (nonatomic) BNE existence result. Addressing (2), we propose two assistant algorithms that sequentially learn from users’ reactions, together with optimality/ convergence guarantees. We validate one of them in a large real-world experiment.} }
Endnote
%0 Conference Paper %T Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory %A Philipp Geiger %A Michel Besserve %A Justus Winkelmann %A Claudius Proissl %A Bernhard Schölkopf %B Proceedings of The 35th Uncertainty in Artificial Intelligence Conference %C Proceedings of Machine Learning Research %D 2020 %E Ryan P. Adams %E Vibhav Gogate %F pmlr-v115-geiger20a %I PMLR %P 207--216 %U https://proceedings.mlr.press/v115/geiger20a.html %V 115 %X We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.), to support coordination between them, and increase efficiency of such collective systems. Key questions are: (1) when and how much can (accurate) predictions help for coordination, and (2) which assistant algorithms reach optimal predictions? First we lay conceptual ground for this setting where user preferences are a priori unknown and predictions influence outcomes. Addressing (1), we establish conditions under which self-fulfilling prophecies, i.e., “perfect” (probabilistic) predictions of what will happen, solve the coordination problem in the gametheoretic sense of selecting a Bayesian Nash equilibrium (BNE). Next we prove that such prophecies exist even in large-scale settings where only aggregated statistics about users are available. This entails a new (nonatomic) BNE existence result. Addressing (2), we propose two assistant algorithms that sequentially learn from users’ reactions, together with optimality/ convergence guarantees. We validate one of them in a large real-world experiment.
APA
Geiger, P., Besserve, M., Winkelmann, J., Proissl, C. & Schölkopf, B.. (2020). Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory. Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, in Proceedings of Machine Learning Research 115:207-216 Available from https://proceedings.mlr.press/v115/geiger20a.html.

Related Material