• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Increasing Entropy to Boost Policy Gradient Performance on Personalization Tasks.

Andrew StarnesAnton DereventsovClayton G. Webster
Published in: ICDM (Workshops) (2023)
Keyphrases
  • policy gradient
  • gradient method
  • model free reinforcement learning
  • neural network
  • control system
  • model checking
  • parametric optimization