Login / Signup

PP-PG: Combining Parameter Perturbation with Policy Gradient Methods for Effective and Efficient Explorations in Deep Reinforcement Learning.

Shilei LiMeng LiJiongming SuShaofei ChenZhimin YuanQing Ye
Published in: ACM Trans. Intell. Syst. Technol. (2021)
Keyphrases
  • reinforcement learning
  • policy gradient methods
  • neural network
  • natural actor critic
  • machine learning
  • learning algorithm
  • function approximation