How Can Creativity Occur in Multi-Agent Systems?
This work addresses the problem of unreliable creativity in multi-agent RL for artists and researchers, but it is incremental as it only proposes criteria without implementation or results.
The paper tackles the challenge of achieving reliable and sophisticated emergent behavior in multi-agent deep reinforcement learning systems by proposing criteria for creativity, aiming to guide artists and spur further research in this area.
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.