Login / Signup

On the consistency of hyper-parameter selection in value-based deep reinforcement learning.

Johan S. Obando-CeronJoão G. M. AraújoAaron CourvillePablo Samuel Castro
Published in: CoRR (2024)
Keyphrases
  • parameter selection
  • reinforcement learning
  • adaptive regularization
  • model selection
  • state space
  • machine learning
  • learning algorithm
  • genetic algorithm
  • kernel ridge regression