Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics

Giovanni Briglia, Francesco Fabiano, Stefano Mariani

Keywords: Multi-Agent Epistemic Planning, Graph-Neural Networks, Learning in Planning, Heuristics

TL;DR: We study the use of GNNs to provide heuristics that guide Multi-Agent Epistemic Planning---where states are represented as Kripke structures---to improve scalability by learning from prior solved instances and capturing structural patterns.

Abstract: Multi-agent Epistemic Planning (MEP) is an autonomous planning framework for reasoning about both the physical world and the beliefs of agents, with applications in domains where information flow and awareness among agents are critical. The richness of MEP requires states to be represented as Kripke structures, i.e., directed labeled graphs. This representation limits the applicability of existing heuristics, hindering the scalability of epistemic solvers, which must explore an exponential search space without guidance, resulting often in untractability. To address this, we exploit Graph Neural Networks (GNNs) to learn patterns and relational structures within epistemic states, to guide the planning process. GNNs, which naturally capture the graph-like nature of Kripke models, allow us to derive meaningful estimates of state quality---e.g., the distance from the nearest goal---by generalizing knowledge obtained from previously solved planning instances. We integrate these heuristics into an epistemic planning pipeline and evaluate them against standard baselines, showing improvements in the scalability of multi-agent epistemic planning.

Area: Search, Optimization, Planning, and Scheduling (SOPS)

Generative A I: I acknowledge that I have read and will follow this policy.

Submission Number: 58