Ikki Tanaka
I have noticed a possible cause from your stacktraces. Are you using the codes of current master branch? I think there are some differences between your script and script in...
Yeah, it's natural. I think this combined version is better than #245 and #246.
Hi @adypd97, thank you for your interest in HandyRL! First of all, after the training server launched, you need to run the workers **in** the VMs for worker: `python main.py...
From your outputs, it seems that the server is not connecting to the workers. Next steps to debug... - Check if it runs correctly on your local machine (localhost) -...
What the worker process/VM looks like? If the workers are still running without any errors, there maybe exist some problems I didn’t watch before.
I like this change if there is no process at entry.
SemVer is cool! When HandyRL is versioned, sounds good.
I agree with adopting this change for more type of games. This may lead widely used.
I like this idea because the optimizer often affects the performance.
Can you imagine the scene we need `prepare_env()`? Loading/downloading master data, building simulator, or special specification...