Deep reinforcement Learning for Atari

Exploring DRDQ learning method for Reinforcement Learning applaied in atari games. Paper.

In this work, we improve the CNN worked with DQN proposed by Deep Mind by using gsurma as baseline.
We add DRQN and GE Heuristics.
We Also use OpenAI Gym

Installation

      sudo apt-get install -y python-numpy python-dev cmake zlib1g-dev libjpeg-dev xvfb ffmpeg xorg-dev python-opengl libboost-all-dev libsdl2-dev swig
      !pip install pyvirtualdisplay
      !pip install piglet
      !pip install gym
      !pip install "gym[atari]"

Citation

@inproceedings{moreno2019atari,
  author={F. {Moreno-Vera}},
  booktitle={2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI)}, 
  title={Performing Deep Recurrent Double Q-Learning for Atari Games}, 
  year={2019},
  pages={1-4},
  doi={10.1109/LA-CCI47412.2019.9036763}
}

Contact us

For any issue please kindly email to felipe [dot] moreno [at] fgv [dot] br