Back
Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory
{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 game-theoretic 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\textquotesingle reactions, together with optimality/convergence guarantees. We validate one of them in a large real-world experiment.}
@inproceedings{item_3151799, title = {{Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory}}, booktitle = {{35th Conference on Uncertainty in Artificial Intelligence (UAI 2019)}}, 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 game-theoretic 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\textquotesingle reactions, together with optimality/convergence guarantees. We validate one of them in a large real-world experiment.}}, volume = {115}, pages = {207--216}, series = {{Proceedings of Machine Learning Research}}, publisher = {Curran}, address = {Tel Aviv, Israel}, year = {2019}, slug = {item_3151799}, author = {Geiger, P and Besserve, M and Winkelmann, J and Proissl, C and Sch\"olkopf, B} }