Login / Signup

Acquiring a broad range of empirical knowledge in real time by temporal-difference learning.

Joseph ModayilAdam WhitePatrick M. PilarskiRichard S. Sutton
Published in: SMC (2012)
Keyphrases
  • temporal difference learning
  • function approximation
  • reinforcement learning
  • prior knowledge
  • fixed point
  • machine learning
  • approximate value iteration
  • decision making
  • monte carlo
  • evaluation function