Login / Signup

Value activation for bias alleviation: Generalized-activated deep double deterministic policy gradients.

Jiafei LyuYu YangJiangpeng YanXiu Li
Published in: Neurocomputing (2023)
Keyphrases
  • fluid model
  • black box
  • cost function
  • fully observable
  • information processing
  • optimal policy
  • active control
  • data sets
  • learning algorithm
  • planning problems