Learning to play slot cars and Atari 2600 games in just minutes

Lionel Cordesses, Omar Bentahar, Julien Page

Feb 15, 2018 (modified: Feb 15, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Machine learning algorithms for controlling devices will need to learn quickly, with few trials. Such a goal can be attained with concepts borrowed from continental philosophy and formalized using tools from the mathematical theory of categories. Illustrations of this approach are presented on a cyberphysical system: the slot car game, and also on Atari 2600 games.
  • TL;DR: Continental-philosophy-inspired approach to learn with few data.
  • Keywords: Artificial Intelligence, Signal processing, Philosophy, Analogy, ALE, Slot Car