Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks
Arthur Juliani


Great article! Tried running the tensorflow example, however I keep getting a 0.0 success rate. Copy pasted your gist in as well and got the same issue. Running it using Python 3.5 on Tensorflow 1.0.1 with gym 0.8.1

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.