How does an artificial neuron work? Inspired by neurons of the human brain, an artificial neuron receives several input values. These input values are multiplied with the weights of the neuron which reflects that some input values are activating the neuron (positive weights) while others inhibit the neuron (negative weights). The product values are then summed and together create the activity a. Finally, a non-linear function is applied on a to yield the final output of the neuron.

Deep Q Learning Today, I want to show you how you can use deep Q learning to let an agent learn how to play a game. Deep Q learning is a method which was introduced by DeepMind in their 2015 Nature paper (pdf) to play Atari video games by just observing the pixels of the game. To make it a bit simpler for the case of this blog post, we will use a slightly easier game which is to balance a polestick on a paddle.