Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • Article
  • Proceedings of the International Conference on Machine Learning (ICML)

Active World Model Learning with Progress Curiosity

By: Kuno Kim, Megumi Sano, Julian De Freitas, Nick Haber and Daniel Yamins
  • Format:Print
ShareBar

Abstract

World models are self-supervised predictive models of how the world evolves. Humans learn world models by curiously exploring their environment, in the process acquiring compact abstractions of high bandwidth sensory inputs, the ability to plan across long temporal horizons, and an understanding of the behavioral patterns of other agents. In this work, we study how to design such a curiositydriven Active World Model Learning (AWML) system. To do so, we construct a curious agent building world models while visually exploring a 3D physical environment rich with distillations of representative real-world agents. We propose an AWML system driven by -Progress: a scalable and effective learning progress-based curiosity signal. We show that -Progress naturally gives rise to an exploration policy that directs attention to complex but learnable dynamics in a balanced manner, as a result overcoming the “white noise problem”. As a result, our -Progress-driven controller achieves significantly higher AWML performance than baseline controllers equipped with state-of-the-art exploration strategies such as Random Network Distillation and Model Disagreement.

Keywords

World Models; Mathematical Methods

Citation

Kim, Kuno, Megumi Sano, Julian De Freitas, Nick Haber, and Daniel Yamins. "Active World Model Learning with Progress Curiosity." Proceedings of the International Conference on Machine Learning (ICML) 37th (2020).
  • Read Now

About The Author

Julian De Freitas

Marketing
→More Publications

More from the Authors

    • March 2025
    • Journal of Experimental Psychology: General

    Is Personal Identity Intransitive?

    By: J. De Freitas and L. J. Rips
    • February 2025
    • New England Journal of Medicine AI

    Disclosure, Humanizing, and Contextual Vulnerability of Generative AI Chatbots

    By: Julian De Freitas and I. Glenn Cohen
    • 2025
    • Scientific Reports

    Humor as a Window into Generative AI Bias

    By: Roger Samure, Julian De Freitas and Stefano Puntoni
More from the Authors
  • Is Personal Identity Intransitive? By: J. De Freitas and L. J. Rips
  • Disclosure, Humanizing, and Contextual Vulnerability of Generative AI Chatbots By: Julian De Freitas and I. Glenn Cohen
  • Humor as a Window into Generative AI Bias By: Roger Samure, Julian De Freitas and Stefano Puntoni
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College.