How Can Creativity Occur in Multi-Agent Systems?

TL;DR

This paper explores how creativity can emerge in multi-agent deep reinforcement learning systems, proposing criteria to guide artists and researchers in fostering innovative behaviors despite training challenges.

Contribution

It introduces criteria for creativity in multi-agent RL and aims to inspire further philosophical and practical investigation into emergent behaviors.

Findings

Proposes criteria for creativity in multi-agent RL

Highlights challenges in training multi-agent systems

Encourages philosophical discussion on emergent creativity

Abstract

Complex systems show how surprising and beautiful phenomena can emerge from structures or agents following simple rules. With the recent success of deep reinforcement learning (RL), a natural path forward would be to use the capabilities of multiple deep RL agents to produce emergent behavior of greater benefit and sophistication. In general, this has proved to be an unreliable strategy without significant computation due to the difficulties inherent in multi-agent RL training. In this paper, we propose some criteria for creativity in multi-agent RL. We hope this proposal will give artists applying multi-agent RL a starting point, and provide a catalyst for further investigation guided by philosophical discussion.