Literature Assignment (SC42050)


This assignment aims to help students in gaining experience with searching for literature and writing a survey. The assignment will be performed in groups of 4 students. You can use the discussion board to get in contact with colleagues and form groups (you must be logged in on Brightspace to use the discussion board).

Assignment material:

  1. General assignment description (2018) (PDF). This description applies to all the assignments; please read it carefully.

  2. Paper review form (DOC). Use this form to review the paper of your group.

  3. Presentation review form (DOC). Use this form to review a presentation tryout of your group.

  4. A unique assignment topic from the list below.

List of assignment topics

Each group of students will choose one topic from this list. Have a look at the topics below, to determine which of them fits your background and preferences best. (If you have problems opening some PDFs, please save them to your hard drive and open them from there.) Instructions on how to sign up for a particular topic will be posted after the start of the course.

Select three topics and send an email to Jens Kober (j dot kober at tudelft dot nl), with the following information:

  • E-mail subject “[SC42050] Literature Assignment”

  • Your names, student numbers, and email addresses

  • The three selected topics with the complete titles and corresponding numbers in decreasing order of preference (i.e., first choice on top). The reason for selecting three topics is to account for the possibility of conflicting selections. If two or more groups select the same first topic, then this topic is given to the group that requested it earliest, while the other group receives their second preference, and so on. To minimize the possibility of such conflicts, topics that are allocated to groups will be removed from the list as soon as possible by changing its status.

You will then receive a confirmation email that contains the title of the (single) assignment topic that has been allocated to your group.

  • To acknowledge their support, we have included the names of the authors of each of the proposed assignments. However, please do not contact them for questions regarding the assignment.

  • *Waiting* in status tells that the group is not complete. Anyone who wants to join needs to negotiate it with the other people and let Jens know. Please, do not overuse it and try to form a group of 4 people yourself.

  • Please post your questions on the Brightspace discussion forum (students from TU Eindhoven or UTwente can send an email instead).

Group ID Topics (link to PDF) Resources Status Students Reviewed by Group
01 Super-human board game playing Paper(1), Paper(2) Taken Patrick Ledzian, Aleksandra Szymanek, Daníel Hjartarson, Máté Bakos 04
02 No Free Lunch Theorems for Optimization Paper Taken Anthony van der Pluijm, Jari Lubberding, Gervase Lovell-Prescod, Jakub Pietrak 13
03 Learning Robust Policies for Control Paper Open
04 Evolution strategies or reinforcement learning? Paper Taken Mees Al, Patrick Nijman, Anoosh Anjaneya Hegde, Arvind Pandit 01
05 Learning Physical Collaborative Robot Behaviors from Human Demonstrations Paper Taken Mark van der Woude, Gyula Max, Tristan Steegman, Joeri Span 36
06 Reusing policies Paper Open
07 Policy gradient reinforcement learning for autonomous robots Paper Taken Sukrit Gupta, Neel Nagda, Shreyas Nikte, Nilay Sheth 08
08 Reinforcement learning for legged robots Paper Taken Joost Zwart, Arthur Helsloot, Lars Kerkhof, Jacques Noom 07
09 Learning Poincaré maps Paper Taken Sam Staps, Floris Meccanici, Roger Moens, Yu Zhang 18
10 Learning from demonstration Paper Open
11 Fuzzy ant colony optimization for optimal control - A comparison to reinforcement learning Paper Taken Frank Gallager, Karst Brummelhuis, Noor van Driel, Tim Hesselmans 12
12 Particle swarm optimization for PID controller design Paper Taken Luuk van Litsenburg, Salomon Voorhoeve, Floris van Dam, Casper Vertregt 11
13 Fuzzy Q-iteration for reinforcement learning Paper Waiting Tiago Nunes, Rohan Chotalal, Francisco Formigão 02
14 Reinforcement learning for HIV treatment Paper Open
15 Least-squares policy iteration for reinforcement learning Paper Waiting Joeri Roelofs, Lex van Dommelen, Rens Slenders 24
16 Evolutionary function approximation for reinforcement learning Paper Open
17 Reinforcement learning for adaptive brain-machine interfaces Paper Taken Ridvan Karagoz, Mohamed Abdelmoumni, Dániel Trombitás, Gabriel König 22
18 Learning to stand up using hierarchical reinforcement learning Paper Taken Martijn van Brakel, Nguyen Hai Anh, Nicolas Manders, Raymond van Dijk 09
19 The role of cooperative agents in a modern warehouse concept Paper Taken Ali Nawaz, Daniel Gedon, Marcin Brunon Kaczmarek, Vasos Arnaoutis 20
20 Artificial intelligence on the IBM Watson computer Taken Paulo Cerqueira, Satyajith Jujjavarapu, Pranav Prakash, Gabriele Tombakaite 19
21 Fuzzy observers for anaerobic WWTP Paper Open
22 Fuzzy controller for measuring blood pressure Paper Taken Jeroen Swart, Max van der Linden, Bas van der Heijden, Mike de Pont 17
23 Takagi-Sugeno descriptor systems Paper Open
24 A sum of squares approach to modeling and control Paper Waiting Han Wopereis, Yifan Shi 15
25 Adaptive neural flight control system for unmanned aircrafts Paper Taken Michael Visser, Bart Hooij, Marc Hogerbrug, Bas van Olffen 26
26 Neural Control System of a Mobile Robot Paper Taken Rick Waasdorp, Arun Thomas, Ashwin George, Aneesh Ashok Kumar 25
27 Hybrid Fuzzy-Neural Networks for Determining Optimal Routing for Communication Networks Paper Taken Ivo Stuldreher, Martijn van der Sar, Jelle Schut, Abhishek Chatterjee 29
28 Fuzzy Controllers for Traffic Intersections Paper(1), Paper(2) Taken Tim Biemans, Bas Dieben, Fons ten Klooster, Niels Uitterdijk 30
29 Application of Artificial Neural Networks in Modeling (e.g. Modeling of Freeway Traffic for Prediction) Paper(1), Paper(2), Paper(3) Waiting Mariona Ruiz Peris, Seline de Rooij, Karin van Schooten 27
30 Reinforcement Learning for Traffic Light Control Paper(1), Paper(2) Taken Vittorio Giammarino, Sara Furioli, Filippo Mafioletti, Georgios Skaltsis 28
31 Active sensing for robotics Paper Taken Anne-Sea van der Zwaag, Thibaut van Bergen, Reinier Prins, Hugo van der Kort 35
32 Distributed Kalman filtering Paper Taken Laura Donadoni, María de la Capilla García Fernández, Swarna Narayanan, Samyuktha Sivaram 34
33 Moving horizon estimation Paper Open
34 Particle filters for tracking robots Paper Taken Marijke van Weperen, Philip Flatz-Stransky, Sribalaji Coimbatore Anand, Jeroen Postma 32
35 Visual and tactile fusion for humanoid robots Paper Taken Emiel Bartels, Geert Bakker, Sjouke de Zwart, Pieter Schuller 31
36 Learning Social Behaviour Paper(1), Paper(2) Taken Bruno Brito, Satish Singh, Roberto Sobhi, Hendrik Wesseling 05

Review Groups

Each group member will also review the paper and/or the presentation of another group. In this way, you will have the possibility to improve the assignment before final submission of the paper and presentation by considering the comments from the other group. A document “Answer to Reviewers” has to be submitted, indicating how the comments from the other group were included (or why not). A table will be posted here which review groups are assigned to each other. In the table above, the review groups are assigned to each other. The deadline for submitting your paper and presentation to each other is March 21 2018, and the deadline for the responses is no later than one week, namely March 28 2018.


The program for the literature symposium will be posted here.
It will be held in the Drebbelweg building. The whole group needs to be present and needs to stay at least for the whole block of 4 or 3 presentations, so coming and leaving is only possible during the break.

Useful links

Search engines for scientific articles: