Generic-to-Specific Reasoning and Learning for Scalable Ad Hoc Teamwork

TL;DR

This paper introduces a hybrid reasoning and learning architecture for scalable ad hoc teamwork, combining knowledge-based and data-driven methods to improve collaboration among agents without prior coordination.

Contribution

It proposes a novel architecture that integrates non-monotonic logical reasoning with learned models and foundation models for effective ad hoc teamwork.

Findings

Effective reasoning with domain knowledge and learned models

Rapid adaptation to new agent behaviors

Improved teamwork performance in VirtualHome environment

Abstract

AI agents deployed in assistive roles often have to collaborate with other agents (humans, AI systems) without prior coordination. Methods considered state of the art for such ad hoc teamwork often pursue a data-driven approach that needs a large labeled dataset of prior observations, lacks transparency, and makes it difficult to rapidly revise existing knowledge in response to changes. As the number of agents increases, the complexity of decision-making makes it difficult to collaborate effectively. This paper advocates leveraging the complementary strengths of knowledge-based and data-driven methods for reasoning and learning for ad hoc teamwork. For any given goal, our architecture enables each ad hoc agent to determine its actions through non-monotonic logical reasoning with: (a) prior commonsense domain-specific knowledge; (b) models learned and revised rapidly to predict the behavior of other agents; and (c) anticipated abstract future goals based on generic knowledge of similar situations in an existing foundation model. We experimentally evaluate our architecture's capabilities in VirtualHome, a realistic physics-based 3D simulation environment.