I gave a talk a PyConSG this year[1], which included a demonstration of training a Reinforcement Learning model on a 'Bubble Breaker' game. There's also more detail available[2].
The Jupyter notebook is included in the GitHub repo[3], and includes a 'scaled down version' that takes ~5mins to train on a MacBook's CPU. There's also a downloadable 'full scale' model that was trained in ~7hours on a Titan X. It plays the game (on average) better than me...
The Jupyter notebook is included in the GitHub repo[3], and includes a 'scaled down version' that takes ~5mins to train on a MacBook's CPU. There's also a downloadable 'full scale' model that was trained in ~7hours on a Titan X. It plays the game (on average) better than me...
[1] http://blog.mdda.net/ai/2016/06/23/workshop-at-pycon-sg-2016 (has slides, and YouTube link) [2] http://redcatlabs.com/2016-07-30_FifthElephant-DeepLearning-... [3] https://github.com/mdda/deep-learning-workshop : have a look at notebooks/7-Reinforcement-Learning.ipynb