Behavior Is Everything: Towards Representing Concepts with Sensorimotor Contingencies

Authors

  • Nicholas Hay Vicarious AI
  • Michael Stark Vicarious AI
  • Alexander Schlegel Vicarious AI
  • Carter Wendelken Vicarious AI
  • Dennis Park Vicarious AI
  • Eric Purdy Vicarious AI
  • Tom Silver Vicarious AI
  • D. Scott Phoenix Vicarious AI
  • Dileep George Vicarious AI

Keywords:

Concept Representation, Hierarchical Reinforcement Learning, Sensorimotor Contingencies, Curriculum Learning, Transfer Learning, Embodied Cognition

Abstract

AI has seen remarkable progress in recent years, due to a switch from hand-designed shallow representations, to learned deep representations. While these methods excel with plentiful training data, they are still far from the human ability to learn concepts from just a few examples by reusing previously learned conceptual knowledge in new contexts. We argue that this gap might come from a fundamental misalignment between human and typical AI representations: while the former are grounded in rich sensorimotor experience, the latter are typically passive and limited to a few modalities such as vision and text. We take a step towards closing this gap by proposing an interactive, behavior-based model that represents concepts using sensorimotor contingencies grounded in an agent's experience. On a novel conceptual learning and benchmark suite, we demonstrate that conceptually meaningful behaviors can be learned, given supervision via training curricula.

Downloads

Published

2018-04-25

How to Cite

Hay, N., Stark, M., Schlegel, A., Wendelken, C., Park, D., Purdy, E., Silver, T., Phoenix, D. S., & George, D. (2018). Behavior Is Everything: Towards Representing Concepts with Sensorimotor Contingencies. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11547

Issue

Section

AAAI Technical Track: Knowledge Representation and Reasoning