Contains Jupyter notebooks associated with the Deep Reinforcement Learning Tutorial given at the O'Reilly 2017 NYC AI Conference.
Required Unity Environments can be downloaded here. Download and unzip the .zip file associated with your OS (ie Linux, Mac, or Windows) and move each of the files within the unzipped folder (ie 2DBall, 3DBall, etc) to the root directory of this repository.
All notebooks and environments tested with Python2 and Python3 on macOS Sierra.
- Tensorflow
- Pillow
- Matplotlib
- numpy
- scipy
- Jupyter
To install dependencies, run:
pip install -r requirements.txt
or
pip3 install -r requirements.txt
If your Python environment doesn't include pip
, see these instructions on installing it.
To launch jupyter, run:
jupyter notebook
Then navigate to localhost:8888
to access each training notebook.
To monitor training progress, run the following from the root directory of this repo:
tensorboard --logdir='./summaries
Then navigate to localhost:6006
to monitor progress with Tensorboard.