What is the simplest model that can account for high-fidelity imitation?

Journal: The Behavioral and brain sciences
PMID:

Abstract

What inductive biases must be incorporated into multi-agent artificial intelligence models to get them to capture high-fidelity imitation? We think very little is needed. In the right environments, both instrumental- and ritual-stance imitation can emerge from generic learning mechanisms operating on non-deliberative decision architectures. In this view, imitation emerges from trial-and-error learning and does not require explicit deliberation.

Authors

  • Joel Z Leibo
    DeepMind, London, UK.
  • Raphael Koster
    Deepmind, London, UK.
  • Alexander Sasha Vezhnevets
    DeepMind, London EC4A 3TW, UK jzl@deepmind.com rkoster@deepmind.com vezhnick@deepmind.com duenez@deepmind.com jagapiou@deepmind.com sunehag@deepmind.com www.jzleibo.com.
  • Edgar A Duénez-Guzmán
    DeepMind, London EC4A 3TW, UK jzl@deepmind.com rkoster@deepmind.com vezhnick@deepmind.com duenez@deepmind.com jagapiou@deepmind.com sunehag@deepmind.com www.jzleibo.com.
  • John P Agapiou
    DeepMind, London EC4A 3TW, UK jzl@deepmind.com rkoster@deepmind.com vezhnick@deepmind.com duenez@deepmind.com jagapiou@deepmind.com sunehag@deepmind.com www.jzleibo.com.
  • Peter Sunehag
    DeepMind, London EC4A 3TW, UK jzl@deepmind.com rkoster@deepmind.com vezhnick@deepmind.com duenez@deepmind.com jagapiou@deepmind.com sunehag@deepmind.com www.jzleibo.com.