Login / Signup

An Improved Off-Policy Actor-Critic Algorithm with Historical Behaviors Reusing for Robotic Control.

Huaqing ZhangHongbin MaYing Jin
Published in: ICIRA (4) (2022)
Keyphrases
  • learning algorithm
  • cost function
  • objective function
  • np hard
  • dynamic programming
  • monte carlo
  • robotic control
  • reinforcement learning
  • search space
  • linear programming
  • mathematical model
  • path planning