Reinforcement Learning

Reinforcment Learning is a branch of machine learning that differs from Supervised learning and Unsupervised learning in that it does not seem to be concerned explicitly with data, but instead with discovering a set of actions \(\pi\) by maximizing a Reward Function over time. Modern reinforcement learning algorithms very frequently involve deep neural networks because of their ability to approximate arbitrary functions.

Algorithms:

Objects:

External Resources:

Notes on reinforcement learning techniques and algorithms