Login / Signup

Investigating the Impact of Action Representations in Policy Gradient Algorithms.

Jan SchneiderPierre SchumacherDaniel F. B. HäufleBernhard SchölkopfDieter Büchler
Published in: CoRR (2023)
Keyphrases
  • learning algorithm
  • natural gradient
  • machine learning
  • policy gradient
  • search algorithm
  • search space
  • support vector machine
  • worst case
  • gradient ascent