Continuous Adaptation in Nonstationary Environments Based on Actor-Critic Algorithm.

Yang Yu Zhixiong Gan Chun Li Hui Luo Jiashou Wang

Published in: ISPACS (2022)

Keyphrases

non stationary
dynamic programming
learning algorithm
np hard
convergence rate
simulated annealing
machine learning
reinforcement learning
objective function
optimal solution
support vector machine svm
parameter estimation
monte carlo
belief state