Derek Tishler

To get resizing of google-chart object to work from inside a Polymer template, I set the css of my chart div to 100% and used the IronResizeableBehavior to trigger on...

Thank you for the quick response! I will give the workaround a try as that sounds like a simple/great solution!

1.Your reward value & gradient are very large. You can compare these to the original Tensorboard of the Doom tutorial to see what I mean. I assume you adjusted the...

The main thing to take away from the doom demo for now, I am guessing, is the Reward magnitude. The original demo A3C-Doom.ipynb uses "r = self.env.make_action(self.actions[a]) / 100.0" You...

Would it be possible to do a much longer run? May I also ask what your learning rate is? Can you try a value one order of magnitude larger(say 1e-3...

To my previous point, can an imbalance arise due to the per frame reward? I worry that this is not instructive. Sure stay alive, but what about wandering around? The...

Looks great before the collapse! Maybe you can stop the training around 1k when things look good and restart/load the model with a lower learning rate or other changes in...

What sort of initialization are you using on your weights? You might get a better answer faster using Xavier initialization, a very popular technique in Tensorflow.. Try setting the initializer/weights_initializer...

I agree and have also read you def don't want to use Xavier with rnn's as well. I think the FC layers would benefit the most. I will give it...

I have also fought allot with using different environments and the network always going off to 1 action and accomplishing nothing. It works well enough for the provided doom example,...