The code written for this report is in Python 3.6
The major dependencies are Numpy, Matplotlib, OpenAI gym with PyBox2D, and PyTorch
A full output of the virtual environment dependencies is listed below as a pip freeze output
Grader should run train.py if they wish to train a baseline model
Grader should run graph.py to visualize training or test curves
Grader should run run.py to see baseline model run on test data
All other files are supplementary
args==0.1.0 Box2D==2.3.1 certifi==2018.8.24 cffi==1.11.5 chardet==3.0.4 click==6.7 clint==0.5.1 cycler==0.10.0 Django==2.0.1 floyd-cli==0.11.11 future==0.16.0 gym==0.10.8 idna==2.7 kiwisolver==1.0.1 marshmallow==2.16.1 matplotlib==3.0.0 mkl-fft==1.0.6 mkl-random==1.0.1 numpy==1.15.2 olefile==0.46 pathlib2==2.3.2 Pillow==5.2.0 pycparser==2.19 pyglet==1.3.2 pyparsing==2.2.1 python-dateutil==2.7.3 pytz==2017.3 PyYAML==3.13 raven==6.9.0 requests==2.19.1 requests-toolbelt==0.8.0 scipy==1.1.0 six==1.11.0 tabulate==0.8.2 torch==0.4.1.post2 torchvision==0.2.1 tornado==5.1.1 urllib3==1.23 virtualenv==16.0.0