riemannian-po-for-lqg
This is an implementation of my paper Dynamic Output-feedback Synthesis Orbit Geometry: Quotient Manifolds and LQG Direct Policy Optimization.
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.1%) to scientific vocabulary
Repository
This is an implementation of my paper Dynamic Output-feedback Synthesis Orbit Geometry: Quotient Manifolds and LQG Direct Policy Optimization.
Basic Info
- Host: GitHub
- Owner: Rainlabuw
- Language: Python
- Default Branch: main
- Size: 234 KB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Riemannian-PO-for-LQG
This is an implementation of the policy optimization algorithm introduced in my paper Dynamic Output-feedback Synthesis Orbit Geometry: Quotient Manifolds and LQG Direct Policy Optimization.
This repo holds the methods for conducting gradient descent (GD) on the Linear-Quadratic-Gaussian (LQG) cost. It also performs Riemannian gradient descent (RGD) with respect to the Krishnaprasad-Martin (KM) metric introduced in the above paper.
LQG_methods.py holds the methods container of everything needed to run policy optimization on your LQG problem setup.
main.py runs a simple GD and RGD on a randomly generated system
experiment.py runs the exact experiment I included in the paper above.
Feel free to ask any questions on confusing parts, or raise issues for hidden bugs! :)
-Spencer Kraisler
Owner
- Name: RAIN Lab
- Login: Rainlabuw
- Kind: organization
- Email: mesbahi@uw.edu
- Location: United States of America
- Repositories: 1
- Profile: https://github.com/Rainlabuw
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: Riemannian-PO-for-LQG
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Spencer
family-names: Kraisler
email: spencerkraisler@gmail.com
affiliation: University of Washington
orcid: 'https://orcid.org/0009-0009-4674-0104'
- given-names: Mehran
family-names: Mesbahi
email: mesbahi@uw.edu
affiliation: University of Washington
repository-code: 'https://github.com/Rainlabuw/Riemannian-PO-for-LQG'
abstract: >-
This is an implementation of my paper Dynamic
Output-feedback Synthesis Orbit Geometry: Quotient
Manifolds and LQG Direct Policy Optimization by Kraisler
and Mesbahi.
This repo is an implementation of gradient descent (GD) on
the Linear-Quadratic-Gaussian (LQG) cost. It also performs
Riemannian gradient descent (RGD) with respect to the
Krishnaprasad-Martin (KM) metric introduced in the above
paper.
keywords:
- machine-learning
- optimization
- optimal-control
- policy-optimization