refactor: adjust learning rate decay timing

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

Closed rickstaa closed 7 months ago

rickstaa commented 7 months ago

This pull request ensures that the learning rate decay occurs after updating the policy, aligning with PyTorch v1.1.0 specifications (see https://github.com/pytorch/pytorch/releases/tag/v1.1.0).