Predicate Invention for Bilevel Planning

TL;DR

This paper introduces a novel algorithm for automatically learning symbolic predicates from demonstrations to improve bilevel planning efficiency in continuous spaces, eliminating manual abstraction design.

Contribution

It proposes a new method to learn predicates automatically via a surrogate objective, enhancing bilevel planning without manual abstraction specification.

Findings

Learned predicates enable faster task solving.

Outperforms six baseline methods in robotic environments.

Effective across four different planning scenarios.

Abstract

Efficient planning in continuous state and action spaces is fundamentally hard, even when the transition model is deterministic and known. One way to alleviate this challenge is to perform bilevel planning with abstractions, where a high-level search for abstract plans is used to guide planning in the original transition space. Previous work has shown that when state abstractions in the form of symbolic predicates are hand-designed, operators and samplers for bilevel planning can be learned from demonstrations. In this work, we propose an algorithm for learning predicates from demonstrations, eliminating the need for manually specified state abstractions. Our key idea is to learn predicates by optimizing a surrogate objective that is tractable but faithful to our real efficient-planning objective. We use this surrogate objective in a hill-climbing search over predicate sets drawn from a grammar. Experimentally, we show across four robotic planning environments that our learned abstractions are able to quickly solve held-out tasks, outperforming six baselines. Code: https://tinyurl.com/predicators-release