Reinforcement Learning (R.L.)
① MDPs (Markov Decision Processes)
② Value Functions
③ Value Iteration
④ Policy Iteration
(both ③ and ④ are algorithms for solving R.L. problems)
Supervised Learning: we have the training set in which we were given sort of the right answer of every training example and it was the just a drop of the learning algorithms to replicate more of the right answers.
Unsupervised Learning: we had just a bunch of unlabeled data just the x's and it was the job in the learning alogrithm to discover so-called structure in the data and several algorithms like cluster analysis K-means, a mixture of all the sort PCA, ICA and so on.
Today we just talk about a different class of learning algorithms between supervised and unsupervised — R.L.
there's a helicopter experiment performed by Andrew Ng at Stanford University(you could see the video and the details of that experiment on the Internet), which is a unmanned helicopter controlld by R.L. algorithms.
It's different from Supervised Learning, because usually we actually do not konw