Kevin Frans
Kevin Frans
Hi, I've pushed an update that should contain the relevant classes from rl-algs
cleaned out the references to tinkerbell, let me know if any libraries still missing
added
Hey, the structure of the repo has been done so it should be easier to install everything. # #
Thanks for the report, I'll look into it. For now: although the output shows "iteration 0", it is continuing the learning process from the checkpoint.
Go ahead and do whatever you want, but I'd appreciate it if you linked back to here. (None of the images are mine though, only the code is)
They take in an array of 64 images, and merge them into one big image, so it's easier to visualize the training results
I'm not 100% sure how PaintsChainer does its thing, but check https://arxiv.org/abs/1704.08834 for how this implementation works
What results are you getting when running it? It seems to be training for me with simply `python main.py` ``` -------- Iteration 0 ---------- Total time: 0.01 mins 408 0.0221478324383...
I'm still working in python 2.7, but with your updated code. Most likely there is a portion of the code that doesn't run properly in python 3. In ilyasu's python3...