Deep learning, reinforcement learning, and world models.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of indispensable factors to achieve human-level or super-human AI systems. On the other hand, both DL and RL have strong connections with our brain functions and with neuroscientific findings. In this review, we summarize talks and discussions in the "Deep Learning and Reinforcement Learning" session of the symposium, International Symposium on Artificial Intelligence and Brain Science. In this session, we discussed whether we can achieve comprehensive understanding of human intelligence based on the recent advances of deep learning and reinforcement learning algorithms. Speakers contributed to provide talks about their recent studies that can be key technologies to achieve human-level intelligence.

Authors

  • Yutaka Matsuo
  • Yann LeCun
    1] Facebook AI Research, 770 Broadway, New York, New York 10003 USA. [2] New York University, 715 Broadway, New York, New York 10003, USA.
  • Maneesh Sahani
    Gatsby Computational Neuroscience Unit, University College London, United Kingdom.
  • Doina Precup
    School of Computer Science, McGill University, 3480 University St., Montreal, Quebec H3A 0E7, Canada. Electronic address: dprecup@cs.mcgill.ca.
  • David Silver
    Google DeepMind, 5 New Street Square, London EC4A 3TW, UK.
  • Masashi Sugiyama
  • Eiji Uchibe
    Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seikacho, Soraku-gun, Kyoto 619-0288, Japan; Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, Okinawa 904-0495, Japan. Electronic address: uchibe@atr.jp.
  • Jun Morimoto
    Dept. of Brain Robot Interface, ATR Computational Neuroscience Labs, Kyoto, Japan.