Skip to content

Shubham1965/Learning_based_Control_Seminar

Repository files navigation

Learning-based Control Seminar 2021-22 WiSe (RWTH Aachen, Germany)

This repository is only for referring to my work for the Seminar Course named "Learning-based Control" held at RWTH Aachen offered by DSME RWTH Institute headed by Prof. Trimpe.

The use of machine learning and artificial intelligence has huge potential for building future engineering systems. Learning-based control is a recent and very active area of research that addresses these challenges, and broadly denotes the intersection of the areas of automatic control and machine learning.

Some topics we would like to cover in this seminar:

  1. Gaussian Processes for dynamics and control.
  2. (Deep) Reinforcement learning.
  3. Structured/Hybrid modeling.
  4. Verification for learning based control.

Goals:

  1. To be able to search, read and understand international, English language research literature.
  2. Understand and explain research problems and their solution.
  3. Present the state of the art of research in written and oral form in English.
  4. Relate the big picture to the details of a technical topic.

Deliverables (all in English):

  1. Paper on the chosen topic (6 pages excl. references).
  2. A review on 2-3 papers of your peers.
  3. Presentation of 20 minutes plus 10 minutes Q&A.

You have to hand in a six-page review paper that contains:

  1. Some background on the broader topic of your paper, incl. helpful references.
  2. The state of the art on the more specific problem, incl. helpful references.
  3. The main contributions and methods used to solve the problem.
  4. A discussion of the presented results.
  5. The paper should be written using LATEX.

Assigned Paper:

  1. Title: Mastering the game of Go with deep neural networks and tree search
  2. Authors: D. Silver et al.
  3. Keywords: Deep Reinforcement Learning
  4. Link: https://www.nature.com/articles/nature16961.pdf
  5. Supervisor: Friedrich Solowjow
  6. Synopsis: This paper is about the famous DeepMind work on mastering Go. In this paper we want to focus on the general idea of RL in combination with presenting the difficulties of the use case problem and some student chosen details. We expect that the student to present the problem, the high level idea, and some in depth details.

Contents of the repo:

  1. LaTeX pdf of my review paper.
  2. Compressed LaTeX folder.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages