A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind
This work addresses the problem of automating ToM for applications in logic, economics, and robotics, offering a novel computational approach that bridges psychological concepts with formal methods.
The paper tackles the challenge of formalizing and automating Theory of Mind (ToM) concepts like goals, intentions, and beliefs by proposing a computational framework based on game theory, which enables bounded rational decision-making while maintaining recursive ToM about others and uses statistical techniques to ensure computability.
Originating in psychology, $\textit{Theory of Mind}$ (ToM) has attracted significant attention across multiple research communities, especially logic, economics, and robotics. Most psychological work does not aim at formalizing those central concepts, namely $\textit{goals}$, $\textit{intentions}$, and $\textit{beliefs}$, to automate a ToM-based computational process, which, by contrast, has been extensively studied by logicians. In this paper, we offer a different perspective by proposing a computational framework viewed through the lens of game theory. On the one hand, the framework prescribes how to make boudedly rational decisions while maintaining a theory of mind about others (and recursively, each of the others holding a theory of mind about the rest); on the other hand, it employs statistical techniques and approximate solutions to retain computability of the inherent computational problem.