Login / Signup

Behavior policy learning: Learning multi-stage tasks via solution sketches and model-based controllers.

Konstantinos TsinganosKonstantinos I. ChatzilygeroudisDenis HadjivelichkovTheodoros KomninosEvangelos DermatasDimitrios Kanoulas
Published in: Future Internet (2022)
Keyphrases
  • multistage
  • learning algorithm
  • online learning
  • active learning
  • learning tasks
  • special case
  • learning systems
  • machine learning
  • optimal solution
  • cost function
  • supervised learning
  • multiple tasks