Maximum reward at 0

[videlille]

Hi

First of all, thanks for this repo
I tried to run your code, the training

The maximum reward is 0, how is it possible?

Thanks

[hardmaru]

Hi! Thanks for playing around with the code. An average score near zero means that the trained agent is basically just as good at playing Slime Volleyball compared to the built-in AI opponent (which is already really good). An average score > zero means that the trained agent is (on average) better than the built-in AI opponent. Since the built-in AI opponent is actually *really* good at the game, it would be virtually impossible to get a score that is substantially higher than zero. I was able to get ~ 1.4 for some of the best agents I trained. If you do anything interesting with this project, please do share with me in the future. Thanks.

…

On Fri, 1 Jul 2022 at 23:30, videlille ***@***.***> wrote: Hi First of all, thanks for this repo I tried to run your code, the training [image: image] <https://user-images.githubusercontent.com/15148955/176914271-9016f503-ab21-4bba-963f-7d1f180b61d5.png> The maximum reward is 0, how is it possible? Thanks — Reply to this email directly, view it on GitHub <#17>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABQGQHXFVLCI2SWPZYMX6PLVR36IVANCNFSM52M5MDLQ> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>