Login / Signup

Multiple peg-in-hole compliant assembly based on a learning-accelerated deep deterministic policy gradient strategy.

Xinwang LiJuliang XiaoWei ZhaoHaitao LiuGuodong Wang
Published in: Ind. Robot (2022)
Keyphrases
  • policy gradient
  • learning algorithm
  • learning process
  • reinforcement learning
  • learning problems
  • supervised learning
  • dynamical systems
  • actor critic