Defining and Mitigating Collusion in Multi-Agent Systems

Abstract

Collusion between learning agents is increasingly becoming a topic of concern with the advent of more powerful, complex multi-agent systems. In contrast to existing work in narrow settings, we present a general formalisation of collusion between learning agents in partially-observable stochastic games. We discuss methods for intervening on a game to mitigate collusion and provide theoretical as well as empirical results demonstrating the effectiveness of three such interventions.

Cite

Text

Foxabbott et al. "Defining and Mitigating Collusion in Multi-Agent Systems." NeurIPS 2023 Workshops: MASEC, 2023.

Markdown

[Foxabbott et al. "Defining and Mitigating Collusion in Multi-Agent Systems." NeurIPS 2023 Workshops: MASEC, 2023.](https://mlanthology.org/neuripsw/2023/foxabbott2023neuripsw-defining/)

BibTeX

@inproceedings{foxabbott2023neuripsw-defining,
  title     = {{Defining and Mitigating Collusion in Multi-Agent Systems}},
  author    = {Foxabbott, Jack and Deverett, Sam and Senft, Kaspar and Dower, Samuel and Hammond, Lewis},
  booktitle = {NeurIPS 2023 Workshops: MASEC},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/foxabbott2023neuripsw-defining/}
}