Towards a Unifying Model of Rationality in Multiagent Systems
This work addresses the challenge of ensuring reliable cooperation in multiagent systems for applications involving AI and human interactions, representing an incremental advancement in modeling agent rationality.
The paper tackles the problem of designing multiagent systems that can effectively cooperate with diverse agents, including humans, by proposing a generic model of socially intelligent agents defined through regret minimization, and shows how to construct such agents for different regret forms to enable robust cooperation.
Multiagent systems deployed in the real world need to cooperate with other agents (including humans) nearly as effectively as these agents cooperate with one another. To design such AI, and provide guarantees of its effectiveness, we need to clearly specify what types of agents our AI must be able to cooperate with. In this work we propose a generic model of socially intelligent agents, which are individually rational learners that are also able to cooperate with one another (in the sense that their joint behavior is Pareto efficient). We define rationality in terms of the regret incurred by each agent over its lifetime, and show how we can construct socially intelligent agents for different forms of regret. We then discuss the implications of this model for the development of "robust" MAS that can cooperate with a wide variety of socially intelligent agents.