Login / Signup

A Prioritized objective actor-critic method for deep reinforcement learning.

Ngoc Duy NguyenThanh Thi NguyenPeter VamplewRichard DazeleySaeid Nahavandi
Published in: Neural Comput. Appl. (2021)
Keyphrases
  • reinforcement learning
  • cost function
  • dynamic programming
  • computational complexity
  • fuzzy logic