World Model for Robot Learning: A Comprehensive Survey

Hugging Face Daily Papers Papers
world-models robot-learning survey reinforcement-learning embodied-ai simulation review

Summary

This comprehensive survey reviews the literature on world models for robot learning, covering their roles in policy learning, planning, and simulation. It highlights key paradigms, benchmarks, and future directions for predictive modeling in embodied agents.

World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have advanced rapidly with the rise of foundation models and large-scale video generation. However, the literature remains fragmented across architectures, functional roles, and embodied application domains. To address this gap, we present a comprehensive review of world models from a robot-learning perspective. We examine how world models are coupled with robot policies, how they serve as learned simulators for reinforcement learning and evaluation, and how robotic video world models have progressed from imagination-based generation to controllable, structured, and foundation-scale formulations. We further connect these ideas to navigation and autonomous driving, and summarize representative datasets, benchmarks, and evaluation protocols. Overall, this survey systematically reviews the rapidly growing literature on world models for robot learning, clarifies key paradigms and applications, and highlights major challenges and future directions for predictive modeling in embodied agents. To facilitate continued access to newly emerging works, benchmarks, and resources, we will maintain and regularly update the accompanying GitHub repository alongside this survey.
Original Article Export to Word Export to PDF
View Cached Full Text

Cached at: 05/13/26, 04:10 AM

Paper page - World Model for Robot Learning: A Comprehensive Survey

Source: https://huggingface.co/papers/2605.00080 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

World models as predictive representations of environmental dynamics have become essential for robot learning, supporting policy learning, planning, and simulation across various embodied applications.

World models, which arepredictive representationsof how environments evolve under actions, have become a central component ofrobot learning. They supportpolicy learning,planning,simulation,evaluation, data generation, and have advanced rapidly with the rise of foundation models and large-scalevideo generation. However, the literature remains fragmented across architectures, functional roles, and embodied application domains. To address this gap, we present a comprehensive review ofworld modelsfrom a robot-learning perspective. We examine howworld modelsare coupled with robot policies, how they serve as learned simulators forreinforcement learningandevaluation, and how robotic videoworld modelshave progressed from imagination-based generation to controllable, structured, and foundation-scale formulations. We further connect these ideas to navigation and autonomous driving, and summarize representative datasets, benchmarks, andevaluationprotocols. Overall, this survey systematically reviews the rapidly growing literature onworld modelsforrobot learning, clarifies key paradigms and applications, and highlights major challenges and future directions for predictive modeling inembodied agents. To facilitate continued access to newly emerging works, benchmarks, and resources, we will maintain and regularly update the accompanying GitHub repository alongside this survey.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2605\.00080

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.00080 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.00080 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.00080 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

World Action Models: The Next Frontier in Embodied AI

Hugging Face Daily Papers

This survey paper introduces World Action Models (WAMs), a unified framework for embodied AI that integrates predictive state modeling with action generation. It provides a taxonomy of existing methods, analyzes the data ecosystem, and outlines evaluation protocols for this emerging paradigm.

A Case for Robot Learning

ML at Berkeley

The article discusses the challenges of programming robots due to Moravec's paradox and proposes robot learning as a solution to enable embodied intelligence.

Learning Visual Feature-Based World Models via Residual Latent Action

Hugging Face Daily Papers

This paper introduces RLA-WM, a visual feature-based world model that leverages residual latent actions and flow matching to efficiently predict future visual states. The method outperforms existing video-diffusion and feature-based approaches while enabling novel robot learning techniques from offline, actionless demonstration videos.

World Models Can Change Everything (20 minute read)

TLDR AI

The article discusses the potential paradigm-shifting impact of world models on AI, highlighting investments by Yann LeCun and Fei-Fei Li in this technology as a successor to the current LLM paradigm.