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
  • 2022
  • Working Paper
  • HBS Working Paper Series

What Would It Mean for a Machine to Have a Self?

By: Julian De Freitas, Ahmet Kaan Uğuralp, Zeliha Uğuralp, Laurie Paul, Joshua B. Tenenbaum and Tomer Ullman
  • Format:Print
  • | Language:English
  • | Pages:37
ShareBar

Abstract

What would it mean for autonomous AI agents to have a ‘self’? One proposal for a minimal notion of self is a representation of one’s body spatio-temporally located in the world, with a tag of that representation as the agent taking actions in the world. This turns self-representation into a constructive inference process of self-orienting, and raises a challenging computational problem that any agent must solve continually. Here we construct a series of novel ‘self-finding’ tasks modeled on simple video games—in which players must identify themselves when there are multiple self-candidates—and show through quantitative behavioral testing that humans are near 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 navigate new settings, and that this is a crucial target for engineers wishing to develop flexible agents.

Keywords

Self; AI; Games; Reinforcement Learning; Avatar; AI and Machine Learning

Citation

De Freitas, Julian, Ahmet Kaan Uğuralp, Zeliha Uğuralp, Laurie Paul, Joshua B. Tenenbaum, and Tomer Ullman. "What Would It Mean for a Machine to Have a Self?" Harvard Business School Working Paper, No. 23-017, September 2022.
  • SSRN
  • Read Now

About The Author

Julian De Freitas

Marketing
→More Publications

More from the Authors

    • 2023
    • Faculty Research

    Summarizing the Mental Customer Journey

    By: Julian De Freitas, Ahmet Uğuralp, Zeliha Uğuralp, Pechthida Kim and Tomer Ullman
    • 2023
    • Faculty Research

    Public Perception and Autonomous Vehicle Liability

    By: Julian De Freitas, Xilin Zhou, Margherita Atzei, Shoshana Boardman and Luigi Di Lillo
    • November 2022 (Revised December 2022)
    • Faculty Research

    Replika AI: Monetizing a Chatbot

    By: Julian De Freitas and Nicole Tempest Keller
More from the Authors
  • Summarizing the Mental Customer Journey By: Julian De Freitas, Ahmet Uğuralp, Zeliha Uğuralp, Pechthida Kim and Tomer Ullman
  • Public Perception and Autonomous Vehicle Liability By: Julian De Freitas, Xilin Zhou, Margherita Atzei, Shoshana Boardman and Luigi Di Lillo
  • Replika AI: Monetizing a Chatbot By: Julian De Freitas and Nicole Tempest Keller
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