MuZero
MuZero copied to clipboard
johan-gras
A structured implementation of MuZero
I want to know if there's a way to play with your trained model. Or how to see if it's working well.
With the current implementation the t parameter does not have an effect on the probabilities. And other implementations also use power. (for example https://github.com/werner-duvaud/muzero-general orhttps://github.com/Zeta36/muzero)
I am trying to train Go using this wonderful project and [GymGo](https://github.com/aigagror/GymGo). However, training.py prints an error at [line 103](https://github.com/intenseG/MuZero/blob/5cab8b6c89b652ad33e277318bfd4389de1315a9/muzero/training/training.py#L103). https://github.com/intenseG/MuZero/blob/5cab8b6c89b652ad33e277318bfd4389de1315a9/muzero/training/training.py#L103 Is there a solution to this error? Thank you....
