Recursive Joint Simulation in Games
This addresses the challenge of fostering cooperation among AI agents in game-theoretic scenarios, though it is incremental as it builds on known results from repeated games.
The paper tackles the problem of achieving cooperation between AI agents in strategic settings by introducing recursive joint simulation, where agents observe nested simulations before acting. The result shows that this interaction is strategically equivalent to an infinitely repeated game, enabling the application of existing folk theorems.
Game-theoretic dynamics between AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to accurately simulate an AI agent, for example because its source code is known. Our aim is to explore ways of leveraging this possibility to achieve more cooperative outcomes in strategic settings. In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation. That is, the agents first jointly observe a simulation of the situation they face. This simulation in turn recursively includes additional simulations (with a small chance of failure, to avoid infinite recursion), and the results of all these nested simulations are observed before an action is chosen. We show that the resulting interaction is strategically equivalent to an infinitely repeated version of the original game, allowing a direct transfer of existing results such as the various folk theorems.