Multi-Agent Interplay in a Competitive Survival Environment
This work addresses the problem of generating human-relevant emergent behavior in multi-agent reinforcement learning, but it is incremental as it builds on existing multi-agent competition approaches.
The paper tackled the challenge of hard-exploration environments in reinforcement learning by developing an extensible competitive multi-agent environment with realistic physics and human-relevant semantics, resulting in the emergence of simple strategies and directions for future improvement.
Solving hard-exploration environments in an important challenge in Reinforcement Learning. Several approaches have been proposed and studied, such as Intrinsic Motivation, co-evolution of agents and tasks, and multi-agent competition. In particular, the interplay between multiple agents has proven to be capable of generating human-relevant emergent behaviour that would be difficult or impossible to learn in single-agent settings. In this work, an extensible competitive environment for multi-agent interplay was developed, which features realistic physics and human-relevant semantics. Moreover, several experiments on different variants of this environment were performed, resulting in some simple emergent strategies and concrete directions for future improvement. The content presented here is part of the author's thesis "Multi-Agent Interplay in a Competitive Survival Environment" for the Master's Degree in Artificial Intelligence and Robotics at Sapienza University of Rome, 2022.