Coordinating users of shared facilities via data-driven predictive assistants and game theory
arXiv:1803.06247
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' reactions, together with optimality/convergence guarantees. We validate one of them in a large real-world experiment.
arXiv commentExtended version, including supplement, of a paper at the 35th Conference on Uncertainty in Artificial Intelligence, 2019
References in corpus (5)
- Sample Complexity of Automated Mechanism Design
- Learning the Structure and Parameters of Large-Population Graphical Games from Behavioral Data
- r-Extreme Signalling for Congestion Control
- Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions
- Multi-agent learning using Fictitious Play and Extended Kalman Filter