noobmaster29

I also plotted all the daily returns for all individual assets in the dataset and there doesn't seem to be any difference that would cause the huge jump seen in...

I haven't checked myself, but note that Zipline only works with Python 3.5 not Python 3.6.

Thank you very much for your help. I was trying to run the code in this notebook: https://nbviewer.jupyter.org/github/Calysto/conx-notebooks/blob/master/work-in-progress/AlphaZero.ipynb I was initially running tensorflow 1 but then "from keras import regularizers"...

The full error when I try to import conx without tensorflow version 2 is: --------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) /anaconda3/envs/rl/lib/python3.7/site-packages/keras/__init__.py in 2 try: ----> 3 from tensorflow.keras.layers.experimental.preprocessing import...

I also logged more information on the training. The actions during training are different (agent is trying all the possible actions). Here is the information for the first 2 episodes:...

LOL, third attempt and now it is only generating [0 0 1 0 0 0 0 0]. Is there something wrong with the inference?

@xiongsenlin No unfortunately, I have not been able to resolve the issue. @HemaZ Argmax should be correct. It takes the highest Q value and turns that action into 1 and...

Yeah, I tried loading the pre-trained network but the agent still doesn't work. Maybe the author could help on getting the notebook to work.

Here's my current solution: 1. download this file: http://www.atarimania.com/rom_collection_archive_atari_2600_roms.html 2. unzip and put the roms folder it in your working (notebook) folder 3. After the first import cell: !python3 -m...

conda install ffmpeg solved this issue for me on Windows.