Planning With Pixels in (Almost) Real Time

Authors

  • Wilmer Bandres Universitat Pompeu Fabra
  • Blai Bonet Universidad Sim ó n Bolívar
  • Hector Geffner ICREA & Universitat Pompeu Fabra

Keywords:

Planning, Width-based Search, Rollouts, Atari, Games

Abstract

Recently, width-based planning methods have been shown to yield state-of-the-art results in the Atari 2600 video games. For this, the states were associated with the (RAM) memory states of the simulator. In this work, we consider the same planning problem but using the screen instead. By using the same visual inputs, the planning results can be compared with those of humans and learning methods. We show that the planning approach, out of the box and without training, results in scores that compare well with those obtained by humans and learning methods, and moreover, by developing an episodic, rollout version of the IW(k) algorithm, we show that such scores can be obtained in almost real time.

Downloads

Published

2018-04-26

How to Cite

Bandres, W., Bonet, B., & Geffner, H. (2018). Planning With Pixels in (Almost) Real Time. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12095