Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

SOE: Fachverband Physik sozio-ökonomischer Systeme

SOE 14: Focus Session: Dynamics of Socio-ecological Systems

SOE 14.5: Vortrag

Mittwoch, 20. März 2024, 12:30–12:50, MA 001

The complex dynamics of collective reinforcement learning — •Wolfram Barfuss — University of Bonn

Cooperation at scale is critical for achieving a sustainable future for humanity. However, achieving collective, cooperative behavior -- in which intelligent actors in complex environments jointly improve their well-being -- remains poorly understood. Complex systems science (CSS) provides a rich understanding of collective phenomena, the evolution of cooperation, and the institutions that can sustain both. Yet, much of the theory in this area fails to consider individual-level complexity and environmental context --- largely for the sake of tractability and because it has not been clear how to do so rigorously. These elements are, however, well-captured in multi-agent reinforcement learning (MARL), which has recently put focus on cooperative (artificial) intelligence. However, typical MARL simulations can be computationally expensive and challenging to interpret.

In this talk, I propose that bridging CSS and MARL affords new directions. By treating MARL as a dynamical system, we can study the complex dynamics of collective cooperation emerging from cognitive agency in a given environmental context.

Keywords: Reinforcement learning; Multi-agent system; Dynamical system; Social-ecological system; Cooperation