ART-AI Seminar
We are pleased to have Jaime Sichman, Professor at the University of São Paulo, join us for this ART-AI seminar entitled ‘Centralized norm enforcement in mixed-motive multiagent reinforcement learning’ at the University of Bath, 1W 2.01, on Monday 5th June 2023, 2.15pm-3.15pm (BST). Julian Padget will chair. See map of the campus for location of 1W. If you are unable to make this event in-person, there is an option to dial in via Microsoft Teams. For more information, please e-mail [email protected].
Title:
Centralized norm enforcement in mixed-motive multiagent reinforcement learning
Abstract:
Mixed-motive games comprise a subset of games in which individual and collective incentives are not entirely aligned. These games are relevant because they frequently occur in real-world and artificial societies, and their outcome is often bad for the involved parties. Institutions and norms offer a good solution for governing mixed-motive systems, but they are usually studied and incorporated into the system in a distributed fashion. We propose a method for reaching socially good outcomes in mixed-motive multiagent reinforcement learning settings by enhancing the environment with a normative system controlled by an external reinforcement learning agent. By employing this method, we show it is possible to reach social welfare even in a system of self-interested agents using only traditional reinforcement learning agent architectures.
