carsten-wenderdel / wildbg

Backgammon engine based on neural networks
https://wildbg.shuttleapp.rs/swagger-ui/
Apache License 2.0
18 stars 5 forks source link

Find out best learning rate for training #15

Open carsten-wenderdel opened 11 months ago

carsten-wenderdel commented 11 months ago

Depending on the size of the neural network, the inputs and the amount of training data different learning rates lead to the best neural network. It would be great, if we don't have manually try that out but if somehow this could be figured out automatically.