Sign in
A Prioritized objective actor-critic method for deep reinforcement learning.
Ngoc Duy Nguyen
Thanh Thi Nguyen
Peter Vamplew
Richard Dazeley
Saeid Nahavandi
Published in:
Neural Comput. Appl. (2021)
Keyphrases
</>
reinforcement learning
cost function
dynamic programming
computational complexity
fuzzy logic