References

Abbeel: Inverse RL slides

link

Lecture slides on Inverse Reinforcement Learning. Contains also very good examples for applications.

Barto: Recent Advances in Hierarchical Reinforcement Learning

link

Very detailed overview on all that was covered regarding HRL.

Scholarpedia on Policy Gradient Methods

link

All the concepts of PG are well explained and the pseudo-code is ease to understand.

Sutton and Barto: Reinforcement Learning: An Introduction

link

One of the most popular textbooks on the subject. Is nice to read and explains the basic concepts. Is freely available online.

TU Darmstadt Slides

link

Special Focus on Natural Policy Gradient

Udacity Course Reinforcement Learning

link

A very good MOOC on the topic that is unfortunately not invoking the latest research as our lecture does. But it has a very good didactic concept and nice instructors.

Wikipedia Markov Decision Process

link

Really good article in the best encyclopaedia