A fuzzy deterministic policy gradient algorithm for pursuit-evasion differential games.

Lixin Wang Maolin Wang Ting Yue

Published in: Neurocomputing (2019)

Keyphrases

learning algorithm
dynamic programming
worst case
computational complexity
np hard
optimal solution
search space
k means
cost function
fuzzy sets
convergence rate
pursuit evasion
reinforcement learning
policy gradient
actor critic
gradient ascent