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): fix learning rate decay defaults #414

Closed rickstaa closed 6 months ago

rickstaa commented 6 months ago

This pull request ensures that the 'lr_decay_type' argument is used when the user doesn't specify the specific learning rate decays.