Synthesized Prioritized Data Pruning based Deep Deterministic Policy Gradient Algorithm Improvement.

Hui Xiang Jun Cheng Qieshi Zhang Jianming Liu

Published in: ICIA (2018)

Keyphrases

search space
computational complexity
learning algorithm
dynamic programming
objective function
monte carlo
gradient ascent
policy gradient
neural network
k means
cost function
np hard
simulated annealing
dynamic environments
support vector machine svm
gradient method