A simple Q-learning Implementation
Q-learning(wiki) is a model-free reinforcement learning technique. The post "A Painless Q-learning Tutorial" provides a clear description and detail steps which give me inspiration to implement it.
note: the original address of the post is expired, I choose a reposted one instead.
To be more general, I use following algorithm to update Q table.
In the original post, learning rate is 1 as default.