Kirsten Crane

I've been intending to switch over to PyTorch for months. Ok thank you will check it out!

If you import train_test_split from sklearn.model_selection you can do something like this ``` # CHANGED JPG TO PNG images = [im for im in os.listdir(args.folder) if im.endswith('.png')] images = np.array(images)...

Is that using the default hyperparameters for their implementation of PPO2? Will give it a go and see what performance is like. If it's not great was thinking of running...

Sure will do. although my guess is that even with optimisation I won't touch SOTA. It seems anything over 900 is using a different paradigm than end-to-end RL, such as...