The recent paper published by Geoffrey Hinton has received a lot of media coverage due to the promising new advancements in the…
So far we have been dealing with a world where, following a certain policy, an agent takes certain actions, but acting in a vacuum state, with no interaction with the outside world.
The goal of reinforcement learning, contrary to the previously seen methods of machine learning (supervised/unsupervised learning), is to tweak the system in order to perform right or wrong in certain ways.
Let’s start with what machine learning is. From the many different descriptions I read and heard, the one that stuck to me the most is the following.
Machine Learning is “computational statistics”; it means building computational artifacts that can…