Wasserstein gradient flows policy optimization via input convex neural networks

Yixuan Wang

doi:10.1117/12.2641331

10 November 2022 Wasserstein gradient flows policy optimization via input convex neural networks

Yixuan Wang

Proceedings Volume 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022); 1234812 (2022) https://doi.org/10.1117/12.2641331
Event: 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 2022, Zhuhai, China

Abstract

Reinforcement learning (RL) is a widely used learning paradigm today. As a common RL method, policy optimization usually updates parameters by maximizing the expected cumulative rewards and other information obtained in the process of environment interaction. To get a better understanding of the RL and its learning theory, there is also proposed that RL can be regarded as the optimal transport problem in a probability measure space. On this basis, we get a large-scale Wasserstein gradient flow RL method by introducing input convex neural networks (ICNNs) to improve the Jordan-Kinderlehrer-otto (JKO) scheme.

Citation Download Citation

Yixuan Wang "Wasserstein gradient flows policy optimization via input convex neural networks", Proc. SPIE 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 1234812 (10 November 2022); https://doi.org/10.1117/12.2641331

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available