Deep RL hands on seminar

Getting started:

Prequisities

pip install tensorflow
pip install gym
sudo apt-get install swig
git clone https://github.com/pybox2d/pybox2d
cd pybox2d
python setup.py build
python setup.py install

Install excercise

git clone https://github.com/amirbar/deep.rl.seminar.git
git checkout {easy/medium/hard}

Choose a track:

Easy:

• neural network model

Medium:

• neural network model
• policy gradients loss function

Hard:

• neural network model
• policy gradients loss function
• model sampling

View solution:

git checkout sol
https://www.youtube.com/watch?v=amDSuZv2tCw&feature=youtu.be

Acknowledgement:

• Code is based on Open AI gym and Tensorflow
• Excercise idea is taken from - TAU Advanced ML class. http://adv-ml-2017.wikidot.com/