Deep Q Network Learning to Play Pong on TensorBoard

floydlabs.com

3 pointsdiegoalejogm4 comments

I built it with PyTorch and is running in FloydHub with GPUs. I suggest you set a smoothing of 0.9 to see the increasing trend :)

Code can be found here: https://github.com/diegoalejogm/deep-q-learning

The link is timing out when I try to access it.

Yeah! Sorry for that, FloydHub has got some errors at the moment and my progress wasn't stored anymore.

You can check out the code here: https://github.com/diegoalejogm/deep-q-learning

It works! I got the models up to the point where FloydHub stopped working. Leave me your mail or something and I can write you to let you know when I upload the training model again! :)

Cool to see you built this on Floydhub! The tensorboard URL is only meant for monitoring running jobs, not for sharing. For showcasing your work, I highly recommend you run your code in jupyter mode and share the notebook instead. Floydhub renders all notebooks into static htmls so you can view it anytime you want. For example, see: https://www.floydhub.com/redeipirati/projects/deep-learning-....

Reply on news.ycombinator.com