Policy Gradient Methods

I have been working with policy gradient methods for more than four years now, starting back in 2001. For a variety of reasons, I implemented many algorithms for policy gradients and also figured out relations between policy gradient algorithms and other, previous algorithms. On this web page, I intend to give researchers and students the possibility to download some software and a few of papers to gain the most important insights. This section has three parts:

1) Example Problems: Problems which we understand and can treat analytically can help us to comprehend what we are doing when we are applying policy gradient methods. These two problems are described among the Case Studies and give links to some code, examples, etc.


3) Literature: While by law, I am not allowed to put any papers on-line for which I do not hold the copyright, I have put a few links to my publications online.

Example Problems

Some stuff