Functional Decision Theory in an Evolutionary Environment
This work addresses decision-making problems for AI agents and humans, presenting an incremental extension of FDT to evolutionary contexts.
The paper explores functional decision theory (FDT) as a normative framework for maximizing utility, showing it outperforms causal and evidential decision theories in classical game theory problems and demonstrating its robustness in an evolutionary environment.
Functional decision theory (FDT) is a fairly new mode of decision theory and a normative viewpoint on how an agent should maximize expected utility. The current standard in decision theory and computer science is causal decision theory (CDT), largely seen as superior to the main alternative evidential decision theory (EDT). These theories prescribe three distinct methods for maximizing utility. We explore how FDT differs from CDT and EDT, and what implications it has on the behavior of FDT agents and humans. It has been shown in previous research how FDT can outperform CDT and EDT. We additionally show FDT performing well on more classical game theory problems and argue for its extension to human problems to show that its potential for superiority is robust. We also make FDT more concrete by displaying it in an evolutionary environment, competing directly against other theories.