# Inequality in Congestion Games with Learning Agents

arXiv: https://arxiv.org/abs/2601.20578 · HTML: https://mlsanity.com/paper/2601.20578/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 52 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [Reinforcement learning based recommender systems: A survey](https://mlsanity.com/paper/2101.06286/) (2021)
- [A Clarification of the Nuances in the Fairness Metrics Landscape](https://mlsanity.com/paper/2106.00467/) (2021)
- [The route to chaos in routing games: When is Price of Anarchy too optimistic?](https://mlsanity.com/paper/1906.02486/) (2019)
- [Follow-the-Regularized-Leader Routes to Chaos in Routing Games](https://mlsanity.com/paper/2102.07974/) (2021)
- [Complexity and Approximation of the Continuous Network Design Problem](https://mlsanity.com/paper/1307.4258/) (2013)
- [Today Me, Tomorrow Thee: Efficient Resource Allocation in Competitive Settings using Karma Games](https://mlsanity.com/paper/1907.09198/) (2019)
- [Segregated interactions in urban and online space](https://mlsanity.com/paper/1911.04027/) (2019)
- [The Design and Analysis of a Mobility Game](https://mlsanity.com/paper/2202.07691/) (2022)
- [Fair Interventions in Weighted Congestion Games](https://mlsanity.com/paper/2311.16760/) (2023)
- [Fair Artificial Currency Incentives in Repeated Weighted Congestion Games: Equity vs. Equality](https://mlsanity.com/paper/2403.03999/) (2024)

## Abstract (arXiv)

Who benefits from expanding transport networks? While designed to improve mobility, such interventions can also create inequality. In this paper, we show that disparities arise not only from the structure of the network itself but also from differences in how commuters adapt to it. We model commuters as reinforcement learning agents who adapt their travel choices at different learning rates, reflecting unequal access to resources and information. To capture potential efficiency-fairness tradeoffs, we introduce the Price of Learning (PoL), a measure of inefficiency during learning. We analyze both a stylized network -- inspired in the well-known Braess's paradox, yet with two-source nodes -- and an abstraction of a real-world metro system (Amsterdam). Our simulations show that network expansions can simultaneously increase efficiency and amplify inequality, especially when faster learners disproportionately benefit from new routes before others adapt. These results highlight that transport policies must account not only for equilibrium outcomes but also for the heterogeneous ways commuters adapt, since both shape the balance between efficiency and fairness.