Distributed Learning for Dynamic Congestion Games

TL;DR

This paper studies how distributed learning affects traffic congestion, revealing that myopic routing policies cause severe inefficiencies, and proposes a novel CHAR mechanism to significantly improve social cost and learning convergence.

Contribution

It introduces the CHAR mechanism that combines hiding and probabilistic recommendations, achieving near-optimal efficiency and better learning in distributed congestion games.

Findings

Myopic routing leads to PoA > 2 and poor learning convergence.

Existing mechanisms fail to improve efficiency or learning.

CHAR mechanism reduces PoA to less than 1.25 and performs well on real data.

Abstract

Today mobile users learn and share their traffic observations via crowdsourcing platforms (e.g., Google Maps and Waze). Yet such platforms myopically recommend the currently shortest path to users, and selfish users are unwilling to travel to longer paths of varying traffic conditions to explore. Prior studies focus on one-shot congestion games without information learning, while our work studies how users learn and alter traffic conditions on stochastic paths in a distributed manner. Our analysis shows that, as compared to the social optimum in minimizing the long-term social cost via optimal exploration-exploitation tradeoff, the myopic routing policy leads to severe under-exploration of stochastic paths with the price of anarchy (PoA) greater than \(2\). Besides, it fails to ensure the correct learning convergence about users' traffic hazard beliefs. To mitigate the efficiency loss, we first show that existing information-hiding mechanisms and deterministic path-recommendation mechanisms in Bayesian persuasion literature do not work with even \(\text{PoA}=\infty\). Accordingly, we propose a new combined hiding and probabilistic recommendation (CHAR) mechanism to hide all information from a selected user group and provide state-dependent probabilistic recommendations to the other user group. Our CHAR successfully ensures PoA less than \(\frac{5}{4}\), which cannot be further reduced by any other informational mechanism. Additionally, we experiment with real-world data to verify our CHAR's good average performance.