Adaptive Coordination in Social Embodied Rearrangement

TL;DR

This paper introduces a new task called Social Rearrangement for multi-agent cooperation in complex environments, and proposes Behavior Diversity Play (BDP), a novel method that improves zero-shot coordination and generalization to new partners.

Contribution

The paper presents BDP, a novel approach that enhances diversity in training behaviors to improve zero-shot coordination in complex multi-agent tasks.

Findings

BDP achieves 35% higher success rate in zero-shot coordination.

BDP improves efficiency by 32% over baseline methods.

Agents trained with BDP generalize well to new partners and environments.

Abstract

We present the task of "Social Rearrangement", consisting of cooperative everyday tasks like setting up the dinner table, tidying a house or unpacking groceries in a simulated multi-agent environment. In Social Rearrangement, two robots coordinate to complete a long-horizon task, using onboard sensing and egocentric observations, and no privileged information about the environment. We study zero-shot coordination (ZSC) in this task, where an agent collaborates with a new partner, emulating a scenario where a robot collaborates with a new human partner. Prior ZSC approaches struggle to generalize in our complex and visually rich setting, and on further analysis, we find that they fail to generate diverse coordination behaviors at training time. To counter this, we propose Behavior Diversity Play (BDP), a novel ZSC approach that encourages diversity through a discriminability objective. Our results demonstrate that BDP learns adaptive agents that can tackle visual coordination, and zero-shot generalize to new partners in unseen environments, achieving 35% higher success and 32% higher efficiency compared to baselines.