Using the Veil of Ignorance to align AI systems with principles of justice.

The philosopher John Rawls proposed the Veil of Ignorance (VoI) as a thought experiment to identify fair principles for governing a society. Here, we apply the VoI to an important governance domain: artificial intelligence (AI). In five incentive-compatible studies (N = 2, 508), including two preregistered protocols, participants choose principles to govern an Artificial Intelligence (AI) assistant from behind the veil: that is, without knowledge of their own relative position in the group. Compared to participants who have this information, we find a consistent preference for a principle that instructs the AI assistant to prioritize the worst-off. Neither risk attitudes nor political preferences adequately explain these choices. Instead, they appear to be driven by elevated concerns about fairness: Without prompting, participants who reason behind the VoI more frequently explain their choice in terms of fairness, compared to those in the Control condition. Moreover, we find initial support for the ability of the VoI to elicit more robust preferences: In the studies presented here, the VoI increases the likelihood of participants continuing to endorse their initial choice in a subsequent round where they know how they will be affected by the AI intervention and have a self-interested motivation to change their mind. These results emerge in both a descriptive and an immersive game. Our findings suggest that the VoI may be a suitable mechanism for selecting distributive principles to govern AI.

Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents.

How do societies learn and maintain social norms? Here we use multiagent reinforcement learning to investigate the learning dynamics of enforcement and compliance behaviors. Artificial agents populate a foraging environment and need to learn to avoid a poisonous berry. Agents learn to avoid eating poisonous berries better when doing so is taboo, meaning the behavior is punished by other agents. The taboo helps overcome a credit assignment problem in discovering delayed health effects. Critically, introducing an additional taboo, which results in punishment for eating a harmless berry, further improves overall returns. This "silly rule" counterintuitively has a positive effect because it gives agents more practice in learning rule enforcement. By probing what individual agents have learned, we demonstrate that normative behavior relies on a sequence of learned skills. Learning rule compliance builds upon prior learning of rule enforcement by other agents. Our results highlight the benefit of employing a multiagent reinforcement learning computational model focused on learning to implement complex actions.

Test-retest reliability of reinforcement learning parameters.

It has recently been suggested that parameter estimates of computational models can be used to understand individual differences at the process level. One area of research in which this approach, called computational phenotyping, has taken hold is computational psychiatry. One requirement for successful computational phenotyping is that behavior and parameters are stable over time. Surprisingly, the test-retest reliability of behavior and model parameters remains unknown for most experimental tasks and models. The present study seeks to close this gap by investigating the test-retest reliability of canonical reinforcement learning models in the context of two often-used learning paradigms: a two-armed bandit and a reversal learning task. We tested independent cohorts for the two tasks (N = 69 and N = 47) via an online testing platform with a between-test interval of five weeks. Whereas reliability was high for personality and cognitive measures (with ICCs ranging from .67 to .93), it was generally poor for the parameter estimates of the reinforcement learning models (with ICCs ranging from .02 to .52 for the bandit task and from .01 to .71 for the reversal learning task). Given that simulations indicated that our procedures could detect high test-retest reliability, this suggests that a significant proportion of the variability must be ascribed to the participants themselves. In support of that hypothesis, we show that mood (stress and happiness) can partly explain within-participant variability. Taken together, these results are critical for current practices in computational phenotyping and suggest that individual variability should be taken into account in the future development of the field.

Social Conformity in Autism.

Humans are extremely susceptible to social influence. Here, we examine whether this susceptibility is altered in autism, a condition characterized by social difficulties. Autistic participants (N = 22) and neurotypical controls (N = 22) completed a memory test of previously seen words and were then exposed to answers supposedly given by four other individuals. Autistic individuals and controls were as likely to alter their judgements to align with inaccurate responses of group members. These changes reflected both temporary judgement changes (public conformity) and long-lasting memory changes (private conformity). Both groups were more susceptible to answers believed to be from other humans than from computer algorithms. Our results suggest that autistic individuals and controls are equally susceptible to social influence when reporting their memories.