Cognitive Models as Simulators: The Case of Moral Decision-Making

TL;DR

This paper proposes using cognitive models as simulators to train AI systems more efficiently, demonstrated through reinforcement learning agents learning fairness in the Ultimatum Game by interacting with a cognitive model of human behavior.

Contribution

It introduces the novel concept of cognitive models as simulators for training AI, specifically applying it to moral decision-making in the Ultimatum Game context.

Findings

RL agents adapt behavior based on simulated emotional states

Using cognitive models reduces training costs and time

Effective for modeling human-like moral decision-making

Abstract

To achieve desirable performance, current AI systems often require huge amounts of training data. This is especially problematic in domains where collecting data is both expensive and time-consuming, e.g., where AI systems require having numerous interactions with humans, collecting feedback from them. In this work, we substantiate the idea of $\textit{cognitive models as simulators}$, which is to have AI systems interact with, and collect feedback from, cognitive models instead of humans, thereby making their training process both less costly and faster. Here, we leverage this idea in the context of moral decision-making, by having reinforcement learning (RL) agents learn about fairness through interacting with a cognitive model of the Ultimatum Game (UG), a canonical task in behavioral and brain sciences for studying fairness. Interestingly, these RL agents learn to rationally adapt their behavior depending on the emotional state of their simulated UG responder. Our work suggests that using cognitive models as simulators of humans is an effective approach for training AI systems, presenting an important way for computational cognitive science to make contributions to AI.