News for hackers. Stuff that matters.

A comment on Reinforcement Learning: From Zero to State of the Art with Pytorch 4.

Re:Reinforcement Learning: From Zero to State of the Art wit... by RobertoG on Friday June 08, 2018 @04:36AM (#17263625)
Pytorch 4?

Pytorch 1 is not available yet.

I suppose it means Pytorch 0.4. but it doesn't sounds so good. We should leave marketing outside technical explanations.

What will happen in the future when there is a Pytorch 4 and somebody find this repo?

[ Parent | on HN ]
Re:Reinforcement Learning: From Zero to State of the Art wit... by Sean1708 on Friday June 08, 2018 @09:08AM (#17264884)
As far as I can tell it's only the Hacker News title that mentions PyTorch 4 (in fact the repo description says "PyTorch0.4 tutorial ..."), and I think it's far more likely that that was just a typo/misunderstanding that some sort of insidious marketing technique.
[ Parent | on HN ]
Re:Reinforcement Learning: From Zero to State of the Art wit... by RobertoG on Friday June 08, 2018 @09:51AM (#17265329)
Maybe I just dreamed it, but I think the description in GitHub said "Pytorch 4". Not anymore.

Well, if it was changed because of my comment, I'm happy to be useful. If it was not changed and I dreamed it, my excuses.

[ Parent | on HN ]