Intra-task Curriculum Learning for Faster Reinforcement Learning in Video Games

  • Nathaniel du Preez-WilkinsonEmail author
  • Marcus Gallagher
  • Xuelei Hu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11320)


In this paper we present a new method for improving reinforcement learning training times under the following two assumptions: (1) we know the conditions under which the environment gives reward; and (2) we can control the initial state of the environment at the beginning of a training episode. Our method, called intra-task curriculum learning, presents the different episode starting states to an agent in order of increasing distance to immediate reward.


  1. 1.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)Google Scholar
  2. 2.
    Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)CrossRefGoogle Scholar
  3. 3.
    Pathak, D., et al.: Curiosity-driven exploration by self-supervised prediction. In: ICML (2017)Google Scholar
  4. 4.
    Chentanez, N., Barto, A.G., Singh, S.P.: Intrinsically motivated reinforcement learning. In: NIPS, pp. 1281–1288 (2005)Google Scholar
  5. 5.
    Dosovitskiy, A., Koltun, V.: Learning to act by predicting the future. In: ICLR (2017)Google Scholar
  6. 6.
    Bengio, Y., et al.: Curriculum learning. In: ICML, pp. 41–48 (2009)Google Scholar
  7. 7.
    van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Nathaniel du Preez-Wilkinson
    • 1
    Email author
  • Marcus Gallagher
    • 1
  • Xuelei Hu
    • 1
  1. 1.School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneAustralia

Personalised recommendations