Multi node training
agi1512 opened this issue · comments
Hello
Do you plan to make it possible to train agent on multiple nodes? I mean on computers that are divided by network. Maybe in form of a league like in original DeepMind paper
Hi, due to that we don't have multi machines at now, we will not try them now. However, we will try to start multi processes to train a league in one single common machine. This may be the feature of the next several versions.
Hi, if there are no problems now, I will close this issue. If you find your problems are not solved, you can re-open this issue at any time.