To Optimize Human-in-the-loop Learning in Repeated Routing Games

TL;DR

This paper introduces a novel recommendation mechanism for repeated routing games that significantly improves social efficiency by reducing the price of anarchy from infinity to near-optimal levels, addressing practical human-in-the-loop learning challenges.

Contribution

It proposes the user-differential probabilistic recommendation (UPR) mechanism, a non-monetary approach that ensures individual rationality and optimizes routing efficiency in repeated, non-myopic scenarios.

Findings

UPR mechanism reduces PoA from infinity to near 1+1/(4N+3).

Theoretical proof of PoA bounds under various information sharing mechanisms.

Experimental validation with real-world datasets confirms near-optimal performance.

Abstract

Today navigation applications (e.g., Waze and Google Maps) enable human users to learn and share the latest traffic observations, yet such information sharing simply aids selfish users to predict and choose the shortest paths to jam each other. Prior routing game studies focus on myopic users in oversimplified one-shot scenarios to regulate selfish routing via information hiding or pricing mechanisms. For practical human-in-the-loop learning (HILL) in repeated routing games, we face non-myopic users of differential past observations and need new mechanisms (preferably non-monetary) to persuade users to adhere to the optimal path recommendations. We model the repeated routing game in a typical parallel transportation network, which generally contains one deterministic path and $N$ stochastic paths. We first prove that no matter under the information sharing mechanism in use or the latest routing literature's hiding mechanism, the resultant price of anarchy (PoA) for measuring the efficiency loss from social optimum can approach infinity, telling arbitrarily poor exploration-exploitation tradeoff over time. Then we propose a novel user-differential probabilistic recommendation (UPR) mechanism to differentiate and randomize path recommendations for users with differential learning histories. We prove that our UPR mechanism ensures interim individual rationality for all users and significantly reduces $\text{PoA}=\infty$ to close-to-optimal $\text{PoA}=1+\frac{1}{4N+3}$, which cannot be further reduced by any other non-monetary mechanism. In addition to theoretical analysis, we conduct extensive experiments using real-world datasets to generalize our routing graphs and validate the close-to-optimal performance of UPR mechanism.