VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Yichao, Kumar, Nishanth, Tang, Hao, Weller, Adrian, Tenenbaum, Joshua B., Silver, Tom, Henriques, João F., Ellis, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909517656096768
author Liang, Yichao
Kumar, Nishanth
Tang, Hao
Weller, Adrian
Tenenbaum, Joshua B.
Silver, Tom
Henriques, João F.
Ellis, Kevin
author_facet Liang, Yichao
Kumar, Nishanth
Tang, Hao
Weller, Adrian
Tenenbaum, Joshua B.
Silver, Tom
Henriques, João F.
Ellis, Kevin
contents Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on both in- and out-of-distribution tasks across five simulated robotic domains. Results show that our approach offers better sample complexity, stronger out-of-distribution generalization, and improved interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23156
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
Liang, Yichao
Kumar, Nishanth
Tang, Hao
Weller, Adrian
Tenenbaum, Joshua B.
Silver, Tom
Henriques, João F.
Ellis, Kevin
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Robotics
Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on both in- and out-of-distribution tasks across five simulated robotic domains. Results show that our approach offers better sample complexity, stronger out-of-distribution generalization, and improved interpretability.
title VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2410.23156