Similarity-Based Cooperation

Caspar Oesterheld, Johannes Treutlein, Roger Baker Grosse, Vincent Conitzer, Jakob Nicolaus FoersterICLR 2023 · OpenReview

Abstract

As ML agents act more autonomously in the world, they will increasingly interact with each other. Unfortunately, in many social dilemmas like the one-shot Prisoner’s Dilemma, standard game theory predicts that ML agents will fail to cooperate with each other. Prior work has shown that one way to enable cooperative outcomes in the one-shot Prisoner’s Dilemma is to make the agents mutually transparent to each other, i.e., to allow them to access one another’s source code (Rubinstein 1997; Tennenholtz 2004) or weights in the case of ML agents. However, full transparency is often unrealistic, whereas partial transparency is commonplace. Moreover, it is difficult to machine-learn to cooperate in the full transparency setting. In this paper, we introduce a more realistic setting in which agents only observe a single number indicating how similar they are to each other. We prove that this allows for the same set of cooperative outcomes as the full transparency setting. We also demonstrate experimentally that cooperation can be learned using simple ML methods.
BibTeX
@inproceedings{oesterheld2023similarity,
  author = {Caspar Oesterheld and Johannes Treutlein and Roger Baker Grosse and Vincent Conitzer and Jakob Nicolaus Foerster},
  title = {{Similarity-Based Cooperation}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=r0LQFDOwfbU},
}

Loading related content...

Figure