ERODE combines continuous depth neural networks (Latent ODEs (Rubanova, 2019)) with ideas from model-based and model-free Reinforcement Learning for control of energy systems. It is hypothesised that the inductive biases enforced by the ODE solver may improve the predictive accuracy of our energy system world model, as compared with other techniques like (Jeen, 2022). This repo was set up to test ideas, and therefore represents the textbook shortcomings one would expect of research code. I apologise for any pain this may cause you.
-
Notifications
You must be signed in to change notification settings - Fork 0
enjeeneer/ERODE
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
ERODE: Emission-Reducing Ordinary Differential Equations
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published