A multi-agent simulator for generating novelty in monopoly

Mayank Kejriwal, Shilpa Thomas

Abstract: Despite impressive advances in Artificial Intelligence (AI)-based gameplaying in recent years, many such systems still lack the capability of robustly dealing with novelty in a sufficiently rich environment. Novelty may be operationally described as the states or situations that violate (implicit or explicit) assumptions about agents, the environment, and agent–agent and agent–environment interactions. In this article, we describe a simulation platform called GNOME (Generating Novelty in Open-World Multi-agent Environments) that was developed to support the development, training and evaluation of AI agents designed to play the strategic four-player board game of Monopoly. Specifically, GNOME evaluates the ability of these agents to detect and react to novelty that is potentially unanticipated by agent developers, and is one of the first gameplaying simulators to treat novelty as a first-class citizen. We hope that its introduction will lead to both practitioner-oriented and fundamental research on the nature of novelty and its impacts on AI gameplaying.