Skip to yearly menu bar Skip to main content


Learning Planning Abstractions from Language

Weiyu Liu · Geng Chen · Joy Hsu · Jiayuan Mao · Jiajun Wu

Halle B #35
[ ] [ Project Page ]
Tue 7 May 1:45 a.m. PDT — 3:45 a.m. PDT


This paper presents a framework for learning state and action abstractions in sequential decision-making domains. Our framework, planning abstraction from language (PARL), utilizes language-annotated demonstrations to automatically discover a symbolic and abstract action space and induce a latent state abstraction based on it. PARL consists of three stages: 1) recovering object-level and action concepts, 2) learning state abstractions, abstract action feasibility, and transition models, and 3) applying low-level policies for abstract actions. During inference, given the task description, PARL first makes abstract action plans using the latent transition and feasibility functions, then refines the high-level plan using low-level policies. PARL generalizes across scenarios involving novel object instances and environments, unseen concept compositions, and tasks that require longer planning horizons than settings it is trained on.

Chat is not available.