The Importance of Credo in Multiagent Learning
This addresses coordination challenges in multiagent learning for applications like robotics or game theory, though it appears incremental as it builds on existing social dilemma frameworks.
The paper tackles the problem of multi-objective optimization in multiagent systems by proposing a 'credo' model that regulates agent behavior for group optimization, finding that globally beneficial outcomes can be achieved without fully aligned interests, with scenarios showing high equality and significantly higher mean population rewards compared to full alignment.
We propose a model for multi-objective optimization, a credo, for agents in a system that are configured into multiple groups (i.e., teams). Our model of credo regulates how agents optimize their behavior for the groups they belong to. We evaluate credo in the context of challenging social dilemmas with reinforcement learning agents. Our results indicate that the interests of teammates, or the entire system, are not required to be fully aligned for achieving globally beneficial outcomes. We identify two scenarios without full common interest that achieve high equality and significantly higher mean population rewards compared to when the interests of all agents are aligned.