Login / Signup

Learning predictive state representations using non-blind policies.

Michael H. BowlingPeter McCrackenMichael JamesJames NeufeldDana F. Wilkinson
Published in: ICML (2006)
Keyphrases
  • predictive state representations
  • dynamical systems
  • learning algorithm
  • reinforcement learning
  • stochastic systems
  • machine learning
  • learning tasks
  • decision making
  • prior knowledge
  • dynamic programming
  • real valued