Beyond Human Intervention: Algorithmic Collusion through Multi-Agent Learning Strategies

TL;DR

This paper investigates multi-agent learning strategies for algorithmic collusion, demonstrating how more complex algorithms can enable automated agents to exploit market dynamics and model other agents' behaviors, addressing practical implementation challenges.

Contribution

It introduces multi-objective learning strategies allowing agents to both exploit market dynamics and model other agents, enhancing the viability of algorithmic collusion.

Findings

Agents can unilaterally exploit market dynamics.

Agents can model other agents' behaviors.

Complex algorithms improve collusion robustness.

Abstract

Collusion in market pricing is a concept associated with human actions to raise market prices through artificially limited supply. Recently, the idea of algorithmic collusion was put forward, where the human action in the pricing process is replaced by automated agents. Although experiments have shown that collusive market equilibria can be reached through such techniques, without the need for human intervention, many of the techniques developed remain susceptible to exploitation by other players, making them difficult to implement in practice. In this article, we explore a situation where an agent has a multi-objective strategy, and not only learns to unilaterally exploit market dynamics originating from other algorithmic agents, but also learns to model the behaviour of other agents directly. Our results show how common critiques about the viability of algorithmic collusion in real-life settings can be overcome through the usage of slightly more complex algorithms.