Similarity-based cooperative equilibrium

November 26, 2022 Β· Declared Dead Β· πŸ› Neural Information Processing Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Caspar Oesterheld, Johannes Treutlein, Roger Grosse, Vincent Conitzer, Jakob Foerster arXiv ID 2211.14468 Category cs.GT: Game Theory Cross-listed cs.AI, cs.LG, cs.MA Citations 7 Venue Neural Information Processing Systems Last Checked 4 months ago
Abstract
As machine learning 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 1998, Tennenholtz 2004) -- or weights in the case of ML agents. However, full transparency is often unrealistic, whereas partial transparency is commonplace. Moreover, it is challenging for agents to learn their way to cooperation 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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Game Theory

R.I.P. πŸ‘» Ghosted

Blockchain Mining Games

Aggelos Kiayias, Elias Koutsoupias, ... (+2 more)

cs.GT πŸ› EC πŸ“š 273 cites 9 years ago

Died the same way β€” πŸ‘» Ghosted