Overcoming the Price of Anarchy by Steering with Recommendations
Cesare Carissimo, Marcin Korecki, Damian Dailisan

TL;DR
This paper investigates how recommender systems can strategically guide self-interested agents in congestion games to achieve socially optimal outcomes, addressing inefficiencies caused by selfish behavior.
Contribution
It introduces the Learning Dynamic Manipulation Problem, demonstrating that strategic recommendations can steer multi-agent reinforcement learning systems toward social optima.
Findings
Strategic recommendations can significantly improve system efficiency.
Increasing recommendation options enhances steering effectiveness.
Recommender systems can robustly influence agent convergence to optimal states.
Abstract
Varied real world systems such as transportation networks, supply chains and energy grids present coordination problems where many agents must learn to share resources. It is well known that the independent and selfish interactions of agents in these systems may lead to inefficiencies, often referred to as the `Price of Anarchy'. Effective interventions that reduce the Price of Anarchy while preserving individual autonomy are of great interest. In this paper we explore recommender systems as one such intervention mechanism. We start with the Braess Paradox, a congestion game model of a routing problem related to traffic on roads, packets on the internet, and electricity on power grids. Following recent literature, we model the interactions of agents as a repeated game between -learners, a common type of reinforcement learning agents. This work introduces the Learning Dynamic…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGame Theory and Applications · Reinforcement Learning in Robotics · Advanced Bandit Algorithms Research
