Modeling Human Cognition with a Hybrid Deep Reinforcement Learning Agent

Human cognition model could help us gain insights in how human cognition behaviors work under external stimuli, pave the way for synthetic data generation, and assist in adaptive intervention design for cognition regulation. When the external stimuli is highly dynamic, it becomes hard to model the effect that how the stimuli influences human cognition behaviors. Here we propose a novel hybrid deep reinforcement learning (HDRL) framework integrating drift-diffusion model to simulate the effect of dynamic time pressure on human cognition performance. We start with a N=50 user study to investigate how different factors may affect human performance, which help us gain prior knowledge in framework design. The evaluation demonstrates that this framework could improve human cognition modeling quantitatively and capture the general trend of human cognition behaviors qualitatively. Our framework could also be extended to explore and simulate how different external factors play a role in human behaviors.