Inter-Agent Relative Representations for Multi-Agent Option Discovery

TL;DR

This paper introduces a novel multi-agent option discovery method using joint-state abstractions that preserve coordination-relevant information, enabling stronger team behaviors in complex environments.

Contribution

It proposes a new approach leveraging the Fermat state and neural graph Laplacian to discover coordinated options without explicit objectives.

Findings

Options improve multi-agent coordination in simulated domains.

The method outperforms existing option discovery techniques.

Team synchronization patterns are effectively captured by the approach.

Abstract

Temporally extended actions improve the ability to explore and plan in single-agent settings. In multi-agent settings, the exponential growth of the joint state space with the number of agents makes coordinated behaviours even more valuable. Yet, this same exponential growth renders the design of multi-agent options particularly challenging. Existing multi-agent option discovery methods often sacrifice coordination by producing loosely coupled or fully independent behaviours. Toward addressing these limitations, we describe a novel approach for multi-agent option discovery. Specifically, we propose a joint-state abstraction that compresses the state space while preserving the information necessary to discover strongly coordinated behaviours. Our approach builds on the inductive bias that synchronisation over agent states provides a natural foundation for coordination in the absence of explicit objectives. We first approximate a fictitious state of maximal alignment with the team, the \textit{Fermat} state, and use it to define a measure of \textit{spreadness}, capturing team-level misalignment on each individual state dimension. Building on this representation, we then employ a neural graph Laplacian estimator to derive options that capture state synchronisation patterns between agents. We evaluate the resulting options across multiple scenarios in two simulated multi-agent domains, showing that they yield stronger downstream coordination capabilities compared to alternative option discovery methods.