Act-to-Ground: A Framework for Symbol Grounding in Planning Domains

Panagiotis Lymperopoulos, Liping Liu

Keywords: Symbol Grounding, planning, weakly supervised learning

TL;DR: In this work we propose Act-to-Ground (A2G), a framework for training grounding models for symbolic planners with weak supervision obtained through environment interaction or demonstrations.

Track: Neurosymbolic Methods for Trustworthy and Interpretable AI

Abstract: Neurosymbolic decision-making agents inherit many of the critical transparency and interpretability benefits of planning-based symbolic agents but also face one of their central challenges: the Symbol Grounding Problem (SGP). Grounding hand-crafted symbolic planning domains to percepts typically requires training models with extensive annotated data which hinders their applicability to broader problems. In this work we propose Act-to-Ground (A2G), a framework for training grounding models for symbolic planners with weak supervision obtained through environment interaction or demonstrations. We first cast the grounding problem as an inference problem and 1) use satisfiability-based planning to provide weak supervision to the grounding model by exploiting knowledge already built into the planning domain, 2) propose an MCMC sampler that enables sampling weak labels for grounding planners, 3) improve neurosymbolic grounding performance via a score-matching objective and 4) propose a learnability condition for learning grounding models for planners.

Paper Type: Long Paper

Submission Number: 50