Artificial Intelligence and the Common Sense of Animals.

Journal: Trends in cognitive sciences
Published Date:

Abstract

The problem of common sense remains a major obstacle to progress in artificial intelligence. Here, we argue that common sense in humans is founded on a set of basic capacities that are possessed by many other animals, capacities pertaining to the understanding of objects, space, and causality. The field of animal cognition has developed numerous experimental protocols for studying these capacities and, thanks to progress in deep reinforcement learning (RL), it is now possible to apply these methods directly to evaluate RL agents in 3D environments. Besides evaluation, the animal cognition literature offers a rich source of behavioural data, which can serve as inspiration for RL tasks and curricula.

Authors

  • Murray Shanahan
    DeepMind, London, UK; Imperial College London, London, UK. Electronic address: m.shanahan@imperial.ac.uk.
  • Matthew Crosby
    Imperial College London, London, UK.
  • Benjamin Beyret
    DeepMind, London, UK. Electronic address: beyret@google.com.
  • Lucy Cheke
    University of Cambridge, Cambridge, UK. Electronic address: lgc23@cam.ac.uk.