VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING

Yichao Liang; Nishanth Kumar; Hao Tang; Adrian Weller; Joshua B. Tenenbaum; Tom Silver; João F. Henriques; Kevin Ellis

VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING

Yichao Liang
, Nishanth Kumar
, Hao Tang
, Adrian Weller
, Joshua B. Tenenbaum
, Tom Silver
, João F. Henriques
, Kevin Ellis

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

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.

Original language	English (US)
Title of host publication	13th International Conference on Learning Representations, ICLR 2025
Publisher	International Conference on Learning Representations, ICLR
Pages	71952-71980
Number of pages	29
ISBN (Electronic)	9798331320850
State	Published - 2025
Event	13th International Conference on Learning Representations, ICLR 2025 - Singapore, Singapore Duration: Apr 24 2025 → Apr 28 2025

Publication series

Name	13th International Conference on Learning Representations, ICLR 2025

Conference

Conference	13th International Conference on Learning Representations, ICLR 2025
Country/Territory	Singapore
City	Singapore
Period	4/24/25 → 4/28/25

All Science Journal Classification (ASJC) codes

Language and Linguistics
Computer Science Applications
Education
Linguistics and Language

Cite this

Liang, Y., Kumar, N., Tang, H., Weller, A., Tenenbaum, J. B., Silver, T., Henriques, J. F., & Ellis, K. (2025). VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING. In 13th International Conference on Learning Representations, ICLR 2025 (pp. 71952-71980). (13th International Conference on Learning Representations, ICLR 2025). International Conference on Learning Representations, ICLR.

Liang, Yichao ; Kumar, Nishanth ; Tang, Hao et al. / VISUALPREDICATOR : LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING. 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, 2025. pp. 71952-71980 (13th International Conference on Learning Representations, ICLR 2025).

@inproceedings{763c43c2e77442f09b5f1612be27660b,

title = "VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING",

abstract = "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.",

author = "Yichao Liang and Nishanth Kumar and Hao Tang and Adrian Weller and Tenenbaum, \{Joshua B.\} and Tom Silver and Henriques, \{Jo{\~a}o F.\} and Kevin Ellis",

note = "Publisher Copyright: {\textcopyright} 2025 13th International Conference on Learning Representations, ICLR 2025. All rights reserved.; 13th International Conference on Learning Representations, ICLR 2025 ; Conference date: 24-04-2025 Through 28-04-2025",

year = "2025",

language = "English (US)",

series = "13th International Conference on Learning Representations, ICLR 2025",

publisher = "International Conference on Learning Representations, ICLR",

pages = "71952--71980",

booktitle = "13th International Conference on Learning Representations, ICLR 2025",

}

Liang, Y, Kumar, N, Tang, H, Weller, A, Tenenbaum, JB, Silver, T, Henriques, JF & Ellis, K 2025, VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING. in 13th International Conference on Learning Representations, ICLR 2025. 13th International Conference on Learning Representations, ICLR 2025, International Conference on Learning Representations, ICLR, pp. 71952-71980, 13th International Conference on Learning Representations, ICLR 2025, Singapore, Singapore, 4/24/25.

VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING. / Liang, Yichao; Kumar, Nishanth; Tang, Hao et al.
13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, 2025. p. 71952-71980 (13th International Conference on Learning Representations, ICLR 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - VISUALPREDICATOR

T2 - 13th International Conference on Learning Representations, ICLR 2025

AU - Liang, Yichao

AU - Kumar, Nishanth

AU - Tang, Hao

AU - Weller, Adrian

AU - Tenenbaum, Joshua B.

AU - Silver, Tom

AU - Henriques, João F.

AU - Ellis, Kevin

PY - 2025

Y1 - 2025

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/105010236583

UR - https://www.scopus.com/pages/publications/105010236583#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:105010236583

T3 - 13th International Conference on Learning Representations, ICLR 2025

SP - 71952

EP - 71980

BT - 13th International Conference on Learning Representations, ICLR 2025

PB - International Conference on Learning Representations, ICLR

Y2 - 24 April 2025 through 28 April 2025

ER -

Liang Y, Kumar N, Tang H, Weller A, Tenenbaum JB, Silver T et al. VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING. In 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR. 2025. p. 71952-71980. (13th International Conference on Learning Representations, ICLR 2025).

VISUALPREDICATOR: LEARNING ABSTRACT WORLD MODELS WITH NEURO-SYMBOLIC PREDICATES FOR ROBOT PLANNING

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this