“Towards Personalized Human AI Interaction—Adapting the Behavior of AI Agents Using Neural Signatures of Subjective Interest”, Victor Shih, David C. Jangraw, Paul Sajda, Sameer Saproo2017-09-14 (brain imitation learning, preference learning; similar)⁠:

Reinforcement Learning AI commonly uses reward/penalty signals that are objective and explicit in an environment—eg. game score, completion time, etc.—in order to learn the optimal strategy for task performance. However, Human-AI interaction for such AI agents should include additional reinforcement that is implicit and subjective—eg. human preferences for certain AI behavior—in order to adapt the AI behavior to idiosyncratic human preferences. Such adaptations would mirror naturally occurring processes that increase trust and comfort during social interactions.

Here, we show how a hybrid brain-computer-interface (hBCI), which detects an individual’s level of interest in objects/events in a virtual environment, can be used to adapt the behavior of a Deep Reinforcement Learning AI agent that is controlling a virtual autonomous vehicle. Specifically, we show that the AI learns a driving strategy that maintains a safe distance from a lead vehicle, and most novel, preferentially slows the vehicle when the human passengers of the vehicle encounter objects of interest. This adaptation affords an additional 20% viewing time for subjectively interesting objects.

This is the first demonstration of how an hBCI can be used to provide implicit reinforcement to an AI agent in a way that incorporates user preferences into the control system.

Similar Links: