Login / Signup

Generalized Critic Policy Optimization: A Model For Combining Advantage Estimates In Actor Critic Methods.

Roumeissa KitouniAbderrahim KitouniFeng Jiang
Published in: ICIP (2020)
Keyphrases
  • gradient method
  • neural network
  • mathematical model
  • actor critic
  • optimization methods
  • reinforcement learning
  • simulated annealing
  • optimization algorithm
  • optimization method
  • function approximation
  • policy gradient