AI4Finance-Foundation / AI4Finance-Foundation/RLSolver

✨ train_obj_model__warm_up__save_load for Tensor Train Task L2O H term

Open
#83 0 comments 0 reactions 0 assignees View on GitHub
discussion
Dominant language
Python
Stars
169
Forks
36
PR merge metrics
No merged PRs in 30d

Description

[train_obj_model__warm_up__save_load.py.txt](https://github.com/AI4Finance-Foundation/ElegantRL_Solver/files/11078391/train_obj_model__warm_up__save_load.py.txt)

`thetas = thetas / thetas.norm(dim=1, keepdim=True)`
This is a very important step↑, which reduces the space of `theta` that we need to search (reduces one degree of freedom)

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.