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
  • December 2023
  • Article
  • Nature Human Behaviour

Self-Orienting in Human and Machine Learning

By: Julian De Freitas, Ahmet Uğuralp, Zeliha Uğuralp, Laurie Paul, Joshua B. Tenenbaum and T. Ullman
  • Format:Print
  • | Pages:14
ShareBar

Abstract

A current proposal for a computational notion of self is a representation of one’s body in a specific time and place, which includes the recognition of that representation as the agent. This turns self-representation into a process of self-orientation, a challenging computational problem for any human-like agent. To examine this process, we created several “self-finding” tasks based on simple video games, in which players (N = 124) had to identify themselves out of a set of candidates in order to play effectively. Quantitative and qualitative testing showed that human players are nearly optimal at self-orienting. In contrast, well-known Deep Reinforcement Learning algorithms, which excel at learning much more complex video games, are far from optimal. We suggest that self-orienting allows humans to flexibly navigate new settings.

Keywords

AI and Machine Learning; Behavior; Learning

Citation

De Freitas, Julian, Ahmet Uğuralp, Zeliha Uğuralp, Laurie Paul, Joshua B. Tenenbaum, and T. Ullman. "Self-Orienting in Human and Machine Learning." Nature Human Behaviour 7, no. 12 (December 2023): 2126–2139.
  • Find it at Harvard
  • Read Now
  • Purchase

About The Author

Julian De Freitas

Marketing
→More Publications

More from the Authors

    • July–August 2025
    • Harvard Business Review

    Don’t Let an AI Failure Harm Your Brand

    By: Julian De Freitas
    • June 2025
    • Faculty Research

    AI and Brand Management: Promises and Perils

    By: Julian De Freitas and Elie Ofek
    • June 2025
    • Nature Machine Intelligence

    Unregulated Emotional Risks of AI Wellness Apps

    By: Julian De Freitas and Glenn Cohen
More from the Authors
  • Don’t Let an AI Failure Harm Your Brand By: Julian De Freitas
  • AI and Brand Management: Promises and Perils By: Julian De Freitas and Elie Ofek
  • Unregulated Emotional Risks of AI Wellness Apps By: Julian De Freitas and Glenn Cohen
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.