I discussed this a bit here: https://www.fast.ai/2017/09/08/introducing-pytorch-for-fasta...
Also some info in the fastai release post: https://www.fast.ai/2018/10/02/fastai-ai/
Re:Practical Deep Learning for Coders 2019
by joshvm on Friday January 25, 2019 @01:42PM
(#19000971)
Once you've done fast.ai, you can look at OpenAI's crash course in reinforcement learning: https://blog.openai.com/spinning-up-in-deep-rl/
Re:Practical Deep Learning for Coders 2019
by chewxy on Friday January 25, 2019 @06:19PM
(#19003564)
If you're interested in a Go version of the AlphaGo algorithm, I wrote one: http://github.com/gorgonia/agogo :)
You can start with this book if you want to go straight to making a gameplay agent
https://www.manning.com/books/deep-learning-and-the-game-of-...
Re:Practical Deep Learning for Coders 2019
by adamnemecek on Friday January 25, 2019 @01:37PM
(#19000909)
The one advantage of pytorch is that you can make your graphs dynamic.
Re:Practical Deep Learning for Coders 2019
by 0101111101 on Friday January 25, 2019 @04:23PM
(#19002607)
Tensorflow also created Eager - their dynamic environment
One question: is there a reason you opted for PyTorch over Keras? I had the impression that Keras was the go-to for "easy as ABC" neural networking.
EDIT: bonus question! I'm really fascinated with gameplay agents like AlphaGo and more recently AlphaStar. If I finish this course, will I have what I need to start work on a toy version of some gameplaying agent? If not, could you recommend where I could go next to start exploring that area?