Login / Signup

Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients.

Mandy GrüttnerFrank SehnkeTom SchaulJürgen Schmidhuber
Published in: ICANN (2) (2010)
Keyphrases
  • multi dimensional
  • game theory
  • optimal policy
  • machine learning
  • computational complexity
  • least squares