hardmaru

Hi! Thanks for playing around with the code. An average score near zero means that the trained agent is basically just as good at playing Slime Volleyball compared to the...

Hi menglin0320 Thanks for the message. If you want to clip by absolute value, rather than global norm, you can just replace the code to tf.clip_by_value, like in this example:...

Okay, I see, so you want to implement a version of vae + gan, based of the normal pixel input, like from Jan's tutorial? Hmm I never had any problems...

Try to add the conditional generation bit, and let us know :-) On Mon, Apr 3, 2017 at 10:19 PM mingwugmail wrote: > Hi, > > (This is more a...

Hi Yes the log loss can go negative Does the model generate sensible handwriting after you have trained it? If you read the paper ok VRNN (Chung etc al 2015),...

Thanks, Sankalp I also had to look thru issues in the original repo when I installed doompy a while back. I recommend asking the creators of the original repo for...

Thanks so much for the detailed instructions! Very helpful On Thu, Jan 17, 2019 at 1:19 PM Xiao Zeng wrote: > I got doom-py to install, and now I am...

Hi @zuoanqh Thanks for the issue. It's due more to laziness on my part, rather than actual requirements to train the VAE. When I was running the experiments I was...

Yeah, that would be great! On Mon, Jan 21, 2019 at 9:32 AM Xiao Zeng wrote: > Thank you so much! I will look into that. should I send a...

It's been a while since I looked at this, but if I remember correctly, for CarRacing-v0, the environment still "renders" something since it needs to rely on OpenGL to spit...