feat(tf2): add alpha/lambda learning rate customization

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

feat(tf2): add alpha/lambda learning rate customization #416

Closed rickstaa closed 6 months ago

rickstaa commented 6 months ago

This pull request enhances user control over the training process by allowing direct customization of the alpha/lambda learning rates and their decay rates. Users can now fine-tune these parameters to suit their specific training requirements better.