Neuro-symbolic General Policy Learning

Neuro-symbolic General Policy Learning

Basics. 
Seminar, 7 graded ECTS points.
The seminar will be run in a block format. There will be an initial meeting on Wednesday, November 13, at 2:15 p.m. All student presentations will be given on Thursday, March 6.

All meetings will take place in room 3.06, Building E1 1. The seminar language is English throughout.

Supervisors for the seminar are Timo P. Gros, Jörg Hoffmann, Daniel Höller, Nicola Müller and Verena Wolf. 

Your task will be to read and understand a piece of research, to write a summary paper in your own words, to give a presentation, and to provide detailed feedback for the paper and presentation of a fellow student.

All email interaction must be pre-fixed with "[NsGPL-24]" in the email subject.

No plagiarism. It is Ok (and encouraged!) to use web resources to further your understanding of your assigned topic. However, using pieces of such material for your summary paper or presentation is inadmissible. Any plagiarism will result in disqualification from the seminar. You are allowed to include pieces (like formal definitions, empirical results tables, or figures) from the paper you are summarizing; however, you need to clearly and explicitly mark such material as being from the paper.

 

Content.
Symbolic AI relies on explicit, human-readable symbols and rules to represent knowledge and solve problems. This approach contrasts with modern, data-driven methods like machine learning, which rely on statistical patterns rather than explicit rules. Recently, both approaches have been combined, leading to the development of neuro-symbolic methods. 
For instance, heuristic search, as a very successful part of symbolic AI, must be applied individually to each instance of a domain/problem. In contrast, neuro-symbolic general policy learning focuses on neural network-based policies that can solve all instances within a specific domain, combining symbolic and data-driven AI benefits. 

In this seminar we will explore the emerging trend of learning neuro-symbolic general policies where the underlying architecture is based on Graph Neural Networks or Transformers.

 

Grading. 
The final grading will be based, in this order of importance, on:

• The quality of your final presentation.
• The quality of your final summary paper.
• The quality of the feedback you provide to your mentee student (see below).
• Your participation in the discussions during the block seminar.
   

Summary Paper. 
For the summary paper, you must use this tex template. You are required to read at least 2 related papers, for the related work section. You are allowed to modify the section structure given in the template if, for whatever reason, this is more adequate for the work you are summarizing. 

The seminar paper should be about 4 pages long (not counting the literature list, and in the double-column format of the template). This is a rough guideline, not a strict rule. If you need, say, 5-6 pages to do your paper justice, then definitely do so.

 

Schedule and Deadlines.

• November 13, 14:15-15:15: Initial meeting. We will give a brief insight into each of the papers.
• November 17: Send a ranked list of the topics you would like to take, by email to Timo. That is, send something like "area 1.2, area 2.2, area 1.1, area 4.2, area 3.1". Please include into this list all topics that you would be willing to accept. The list must contain at least 5 topics.

  Note that each topic is associated with a mentee student (to whom you will provide feedback, see the following deadlines); and a mentor student (who will provide feedback to you, see the following deadlines). The mentee/mentor assignment will be a "cycle" through each of the topic areas: within the k topics of each area, the mentor->mentee relation is i->i+1 and k->1. If you want to team up with someone specific, please do state that in your email.

• November 18: Receive your topic. Read the material associated with your topic carefully, and prepare an initial version of your summary paper, using the tex template given above.
• December 9: Deadline for official registration to this seminar (exam registration, Prüfungsanmeldung).
• December 9 - December 13: Make an appointment with your supervisor (as listed with each paper) to discuss your paper. The purpose of this meeting is to ensure that you understood the paper correctly, and to ask questions about specific points.

  NOTE: The following deadlines marked with "(ca.)" are meant as a guideline. You are required to do these things, but if you do them 3-4 days earlier or later, that is no problem.

• January 3 (ca.): Send your summary paper to your mentor student (cc supervisor).
• January 10 (ca.): Send feedback regarding the summary paper to your mentee student (cc supervisor).
• January 17 (ca.): Send revised summary paper to your mentor student (cc supervisor).
• January 24 (ca.): Send feedback regarding the revised summary paper to your mentee student (cc supervisor).
• January 31 (ca.): Send presentation slides to mentor student (cc supervisor).
• February 7 (ca.): Send feedback regarding the presentation slides to your mentee student (cc supervisor).
• February 14 (ca.): Send revised presentation slides to mentor student (cc supervisor).
• February 21 (ca.): Send feedback regarding the revised presentation slides to your mentee student (cc supervisor).

   

• February 28: Send your final summary paper by email to your supervisor.
• March 6: Give a presentation (20 minutes talk, plus 10 minutes discussion) in the block seminar. Attendance to all talks is required. Please try to stick to the 20 minutes time slot for your talk; it should not be a lot shorter, nor a lot longer.

   

Topics.
Find the list of topics here.