Seminar: Trusted AI Planning

Dr. Daniel Höller, Prof. Dr. Jörg Hoffmann

News

Currently, no news are available

Seminar: Trusted AI Planning

 

Basics. Seminar, 7 graded ECTS points.

The seminar will be run in a block format. All meetings will take place in room 3.06, Building E1 1. The seminar language is English throughout. There will be an initial meeting on Monday, October 26, 16:00 - 17:00. All student presentations will be given on some day after the lecture's period (which ends Friday February 05) -- the exact date will be set once the seminar assignment is final to avoid any conflicts with exam dates.

All email interaction must be pre-fixed with "[TAIP26]" in the email subject.

Supervisors for the seminar are Daniel Höller and Jörg Hoffmann. Additional feedback will be provided by Jan Eisenhut, Songtuan Lin, Victor Scherer Putrich and Marcel Vinzent. For organizational questions please contact Victor Scherer Putrich.

Your task will be

  1. to read and understand a research topic (see below), to write a summary paper in your own words and to give a presentation.
  2. to provide detailed feedback for the paper and presentation of a fellow student.

No plagiarism, no LLMs. It is Ok (and encouraged) to use web resources to further your understanding of your assigned topic. However, it is inadmissible to use pieces of public material for your summary paper or presentation, and it is not allowed to generate parts of your slides or summary paper using LLMs. Any plagiarism or LLM use 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. AI Planning is the sub-area of AI concerned with complex action-choice problems. The seminar covers methods supporting trust in algorithmic solutions to such problems. This field of research is very recent, and we cover research conducted in the FAI group. A major concern are neural action policies, i.e., neural networks that map states to actions. While such policies can be very performant, they are fundamentally opaque and come without any guarantees. We cover methods for verifying, testing, and re-training such policies.

Prerequisites. Participants must have successfully completed either an edition of the Artificial Intelligence core course, or of the (Trusted) AI Planning specialized course.

Registration. Is via the central seminar registration system.

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 (and your participation in the feedback process in general, see below).
  • Your participation in the discussions during the block seminar.

You must fulfill each of these task to pass the 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 topic justice then definitely do so.

Presentation. Your talk should be roughly 20 minutes (not a lot longer, not a lot shorter). It will be accompanied by 10 minutes for discussion. For your presentation slides you are encouraged to use this tex template (or any other tex template).

Schedule and Deadlines (tentative!).

The following deadlines are firm:

  • October 26, 16:00 - 17:00: Initial meeting. We will give a brief insight into each of the papers.
  • October 28: Choose your preferences (via the Tutorial mechanism in the CMS).
  • October 30: Receive your topic (as tutorial slots in the CMS). 
  • After topic assignment: Read the material associated with your topic carefully. 
  • November (x): Deadline for official registration to this seminar (exam registration, Prüfungsanmeldung).
  • November 23-27 Meeting with your feedback-giver (as listed with each paper) to discuss your paper. The purpose of this meeting is to ensure that you understood the topic correctly, and to ask questions about specific points. You should bring along notes about what you do not yet fully understand. You can also bring a first outline of your summary paper and/or presentation, and discuss this at the meeting. It is within your responsibility to contact your feedback giver to schedule the meeting. 
  • February 10 Upload your final summary paper in the CMS.
  • February 16 (day before block seminar): Upload your final presentation slides in the CMS.
  • February (to be decided) Block seminar with presentations. Attendance to all talks is required.

The following deadlines are a rough guideline (indicated by "(ca.)"). You are required to fulfill these tasks.

  • January 8 (ca.): Send presentation slides and summary paper to mentor student (cc supervisor and feedback giver).
  • January 15 (ca.): Send feedback regarding the presentation slides and summary paper to your mentee student (cc supervisor and feedback giver).
  • January 22 (ca.): Send revised presentation slides and summary paper to mentor student (cc supervisor and feedback giver).
  • January 29 (ca.): Send feedback regarding the revised presentation slides and summary paper to your mentee student (cc supervisor and feedback giver).

Email communication: To avoid confusion, please use the following subject format when sending you summary paper, presentation slides or feedback:

[TAIP26] <Type> -  <Summary|Presentation> - Topic <X> - <Student Name>

where <type> is one of:

  • Submission 1
  • Submission 2
  • Feedback 1
  • Feedback 2

For example: [TAIP26] Submission 1 - Presentation  - Topic 6 - Marcel Vinzent

Topics. Each participant will be assigned one topic, most of which consists of one paper. The overall amount and difficulty of the material associated with each topic is roughly balanced.

Each topic is associated with a mentee student (to whom you will provide feedback, see the deadlines above) and a mentor student (who will provide feedback to you, see deadlines). The mentee/mentor assignment will be a "cycle" through each of the topic areas as listed below: let k be the number of topics in an area, then the mentor->mentee relation is i->i+1 and k->1.

NOTE: All papers can be freely accessed from within the university's vpn.

Area 1: Open-Loop Verification (supervisor: Jörg Hoffmann, feedback giver: Marcel Vinzent)

Area 2: Closed-Loop Verification (supervisor: Daniel Höller, feedback giver: Victor Scherer Putrich)

Area 3: Testing (supervisor: Daniel Höller, feedback giver: Jan Eisenhut)

Area 4: Repair (supervisor: Jörg Hoffmann, feedback giver: Songtuan Lin)

Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators.