News for hackers. Stuff that matters.
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @02:44PM (#16233910)
PyTorch code: https://github.com/diegoalejogm/deep-q-learning

I'll add final results and performance videos soon!

[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by paulgb on Thursday January 25, 2018 @05:09PM (#16235168)
Neat! Of note: if I'm reading correctly, this is learning to play the video game pong with no prior knowledge using the screen pixels alone. Pretty cool.
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @05:12PM (#16235197)
Yeah! I couldn't have described it better than you just did!

Feel free to take a look at the code and star the code if you like it. I'll keep upgrading it and adding more Reinforcement Learning variations

[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @06:48PM (#16235859)
Forgot to mention that it is learning from raw pixels!! No other info is passed to the agent, except the screen frames :)
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @03:44PM (#16234480)
Also, you can check the FloydExecution in: https://www.floydhub.com/diegoalejogm/projects/atari/29
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @03:47PM (#16234511)
Also, it will be training for several hours more (I approximate 20), so make sure to keep updated. I'll post videos on the current execution performance.
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by ghop02 on Thursday January 25, 2018 @03:48PM (#16234513)
The help link doesn't work for me, did the github repo change?
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @03:49PM (#16234532)
No, it hasn't. Here: http://github.com/diegoalejogm/deep-q-learning

Try again and let me know if this time it works :)

[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by ghop02 on Thursday January 25, 2018 @04:00PM (#16234617)
Ah, I'm new to tensorboard. The help link in tensorboard was broken. But that link works :) very cool!
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @05:14PM (#16235211)
No worries! Here's also a link to the current progress https://www.floydhub.com/diegoalejogm/projects/atari/29 in case you wanna check the machine usage too
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by houqp on Thursday January 25, 2018 @07:13PM (#16236009)
Just so you know, machine stats feature is not ramped to all the users yet, so most of them won't be able to see the fancy UI you were seeing. We will push it out to all users late next week ;)
[ Parent | on HN ]
Re:AI Learning How to Play Pong in RealTime – PyTorch by diegoalejogm on Thursday January 25, 2018 @08:09PM (#16236265)
Good to know :) Thanks for the info, I'll have that in mind for the following posts!
[ Parent | on HN ]