This code follows the description of the Deep Q Learning algorithm described in Playing Atari with Deep Reinforcement Learning [2] and shows that this learning algorithm can be further used in playing maze games.
The agent is expected to find the best way going to 'room 8' from 'room 1' after its adventure in the maze.
Python 2.7 TensorFlow 0.7
git clone https://github.com/dorje/maze.git
cd maze
python playMaze.py
[1] Mnih Volodymyr, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. Human-level Control through Deep Reinforcement Learning. Nature, 529-33, 2015.
[2] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing Atari with Deep Reinforcement Learning. NIPS, Deep Learning workshop
This work is highly based on the following repo: https://github.com/yenchenlin/DeepLearningFlappyBird