Learning Norms from Stories: A Prior for Value Aligned Agents
This addresses value alignment for AI agents, but it is incremental as it introduces a complementary technique to existing methods.
The paper tackles the problem of value alignment in AI agents by learning a prior from societal norms encoded in children's comic strips, achieving performance in classification tasks and demonstrating transferability to unrelated tasks with minimal additional training.
Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans. Traditional approaches to value alignment use imitation learning or preference learning to infer the values of humans by observing their behavior. We introduce a complementary technique in which a value aligned prior is learned from naturally occurring stories which encode societal norms. Training data is sourced from the childrens educational comic strip, Goofus and Gallant. In this work, we train multiple machine learning models to classify natural language descriptions of situations found in the comic strip as normative or non normative by identifying if they align with the main characters behavior. We also report the models performance when transferring to two unrelated tasks with little to no additional training on the new task.