search

rickstaa / stable-learning-control

A framework for training theoretically stable (and robust) Reinforcement Learning control algorithms.
https://rickstaa.dev/stable-learning-control
MIT License
6 stars 1 forks source link

fix(pytorch): ensure correct application of constant learning rate #411

Closed rickstaa closed 6 months ago

rickstaa commented 6 months ago

This pull request rectifies an issue with the constant learning rate scheduler. Previously, the constant learning rate was not being applied as expected when selected by the user. This fix ensures that the scheduler correctly maintains a constant learning rate throughout the training process when it's chosen.