Alternated Greedy-Step Deterministic Policy Gradient.

Xuesong Wang Jiazhi Zhang Yang Gu Longyang Huang Kun Yu Yuhu Cheng

Published in: IEEE Trans. Cogn. Dev. Syst. (2023)

Keyphrases

policy gradient
search algorithm
reinforcement learning
gradient method
actor critic
parametric optimization
model free reinforcement learning
dynamic programming
sufficient conditions
function approximation
reinforcement learning algorithms