Double Q-learning reinforcement learning agent on NES Super Mario Bros

Primary LanguagePython

Reinforcement Learning on Super Mario Bros (NES)

Reinforcement learning is currently one of the hottest topics in machine learning. For a recent conference we attended (the awesome Data Festival in Munich), we've developed a reinforcement learning model that learns to play Mario Bros on NES so that visitors, that come to our booth, can compete against the agent in terms of level completion time.

The promotion was a great success and building the model was a lot of fun. So, I decided to write a blog post about it that covers some of the fundamental concepts of reinforcement learning as well as the actual implementation in TensorFlow.