Hi all,
I would like to use single-player AlphaZero
, but it does not work as conveniently as other algorithms like PPO
. I wonder if anyone has a script or a notebook using AlphZero
with Ray’s tuner
or trainer
?
Thanks!
Hi all,
I would like to use single-player AlphaZero
, but it does not work as conveniently as other algorithms like PPO
. I wonder if anyone has a script or a notebook using AlphZero
with Ray’s tuner
or trainer
?
Thanks!
There is no example python script, but a tuned example. This tuned example obviously translated to a python script.
If you play around with it and procude a cool learning example using tune, please share it within the scope of a PR though.