Login / Signup

Learning from Demonstrations: Is It Worth Estimating a Reward Function?

Bilal PiotMatthieu GeistOlivier Pietquin
Published in: ECML/PKDD (1) (2013)
Keyphrases
  • learning process
  • active learning
  • inverse reinforcement learning
  • learning algorithm
  • reinforcement learning
  • data mining
  • machine learning
  • pairwise
  • prior knowledge
  • supervised learning
  • partially observable