Login / Signup

Actor-only Deterministic Policy Gradient via Zeroth-order Gradient Oracles in Action Space.

Harshat KumarDionysios S. KalogeriasGeorge J. PappasAlejandro Ribeiro
Published in: ISIT (2021)
Keyphrases
  • policy gradient
  • reinforcement learning
  • reinforcement learning algorithms
  • action space
  • reinforcement learning methods
  • machine learning
  • dynamic environments