Relational Forward Models for Multi-Agent Learning

TL;DR

This paper introduces Relational Forward Models (RFM), which predict agent behaviors in multi-agent systems, providing interpretable insights and faster learning, crucial for developing autonomous, cooperative agents.

Contribution

The paper presents RFM as a novel approach that leverages environment relations for interpretable predictions and improved learning speed in multi-agent systems.

Findings

RFM produces accurate behavior predictions in multi-agent environments.

Embedding RFM accelerates agents' learning compared to baselines.

RFM offers interpretable insights into social interactions.

Abstract

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predictions of agents' future behavior in multi-agent environments. Because these models operate on the discrete entities and relations present in the environment, they produce interpretable intermediate representations which offer insights into what drives agents' behavior, and what events mediate the intensity and valence of social interactions. Furthermore, we show that embedding RFM modules inside agents results in faster learning systems compared to non-augmented baselines. As more and more of the autonomous systems we develop and interact with become multi-agent in nature, developing richer analysis tools for characterizing how and why agents make decisions is increasingly necessary. Moreover, developing artificial agents that quickly and safely learn to coordinate with one another, and with humans in shared environments, is crucial.