Emotion-Driven Reinforcement Learning
Robert Marinier, John E. Laird · eScholarship (California Digital Library) · 2008
Existing computational models of emotion are primarily concerned with creating more realistic agents, with recent efforts looking into matching human data, including qualitative emotional responses and dynamics.In this paper, our work focuses on the functional benefits of emotion in a cognitive system where emotional feedback helps drive reinforcement learning.Our system is an integration of our emotion theory with Soar, an independently-motivated cognitive architecture.