Riemannian Proximal Policy Optimization

Shijun Wang, Baocheng Zhu, Chen Li, Mingzhe Wu, James Zhang, Wei Chu and Yuan Qi

Computer and Information Science, 2020, vol. 13, issue 3, 93

Abstract: In this paper, we propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and formulate it as a non-convex optimization problem in the Riemannian space of positive semidefinite matrices. For two given policy functions, we also provide its lower bound on policy improvement by using bounds derived from the Wasserstein distance of GMMs. Preliminary experiments show the efficacy of our proposed Riemannian proximal policy optimization algorithm.

Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.ccsenet.org/journal/index.php/cis/article/download/0/0/43372/45455 (application/pdf)
http://www.ccsenet.org/journal/index.php/cis/article/view/0/43372 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ibn:cisjnl:v:13:y:2020:i:3:p:93

Access Statistics for this article

More articles in Computer and Information Science from Canadian Center of Science and Education Contact information at EDIRC.
Bibliographic data for series maintained by Canadian Center of Science and Education ().