Cultural Algorithm Guided Policy Gradient with Parameter Exploration.

Mark Nuppnau Khalid Kattan Robert G. Reynolds

Published in: AAAI Spring Symposia (2024)

Keyphrases

learning algorithm
search space
dynamic programming
optimization algorithm
objective function
k means
computational complexity
np hard
simulated annealing
convergence rate
cost function
worst case
monte carlo
path planning
policy gradient