I will introduce generalized empowerment maximization—an information-theoretic framework for modeling intrinsic motivation. I’ll show how to compute empowerment under practical approximations. I will then show how agents driven by this objective can solve standard control problems with no external rewards. Extending this to multi-agent settings, I will present numerical experiments showing how such agents interacting can give rise to qualitatively diverse behaviors—from antagonism to cooperation—reminiscent of living systems. A mathematical understanding of these phenomena is still waiting to be found.

—

To request the Zoom link send an email to jteeters@berkeley.edu.  Also indicate if you would like to be added to the Redwood Seminar mailing list.