yuricat / muzerojupyterexample Goto Github PK

Hi，Yuri！how are you there? and I want to know about your recent progress in Muzero project, has your model converged？I built my Muzero to play renju，but after several hundred epochs of training, it still showed little enhancement too, which makes me kind of frustrated, would you share with me some intermediate output of the model such as hideen status, the predicated probability or evaluated value of one particular board configuration? we can communicate each other and analyse the problem

How about implement cuda support?

I'm trying to fill the pseudocode.py DeepMind attached to its paper about MuZero. for the network part I used a very similar structure to yours in this repository but I'm not able to make the training process to converge.

By the way, I tried with Connect4 game instead of tic-tac-toe.

Could you please @YuriCat take a look just in case I made some mistake? https://github.com/Zeta36/muzero

Thank you!!

respected author:
i have a puzzle that the three components: representation and dynamics as well as prediction network are constructed in one big conv network?
if they work seperately ,how to train them jointly and in 'end to end' fashion?
can you figure it out?