Hi Arthur,
Marko Simić
11

Hi Marko,

Thanks for your comments.

The code in the tutorial was meant as instructive rather than production-level code. I implemented A3C in a way that I thought would be simple and understandable for a general audience. Running as truly separate processes would indeed provide a speed increase. I am always happy to accept pull requests for any of my tutorials on Github.

In my code each worker is indeed running on a separate core though. Attached is an image of CPU usage during and after running my A3c implementation. As you can see each of the cores is being utilized.

As for the resources I use, I am not sure where I mentioned only using a laptop. For my lab-research I use a dedicated machine with a Titan X Pascal. I also recently began work at a company where we are using cloud GPUs. You are right that anyone with only a laptop would likely be severely limited in the Deep Learning research they could conduct.

Like what you read? Give Arthur Juliani a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.