@inproceedings{f8fdd4dd4b094c53b2ce71a5f51e2c53,
title = "Generalized Critic Policy Optimization: A Model for Combining Advantage Estimates in Actor Critic Methods",
abstract = "We present a general model for actor critic methods that represent the possibility of combining value function estimations as a means to further reduce the policy gradient's variance and improve the learning result. We show the potential of this architecture by implementing an example case to learn some of the Pybullet continous control robotic tasks with OpenAI Gym. We show by experimenting with a special case the effect of the external parameters on the overall performance of the policy optimization algorithm.",
keywords = "actor critic, advantage estimation, deep reinforcement learning, policy gradient",
author = "Roumeissa Kitouni and Abderrahim Kitouni and Feng Jiang",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Image Processing, ICIP 2020 ; Conference date: 25-09-2020 Through 28-09-2020",
year = "2020",
month = oct,
doi = "10.1109/ICIP40778.2020.9190994",
language = "英语",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3184--3188",
booktitle = "2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings",
address = "美国",
}