In the project, you will gain practical experience with Learning Architectures for Artificial Intelligence in simulated environments, apply neural networks, and human-brain inspired approaches (visual search, attention-based mechanisms, symbolic reasoning) to learn and produce complex purposeful actions in the context of one of the following environments on your choice [1-8].
[1] PHYRE: https://player.phyre.ai
[2] Minecraft: https://www.aicrowd.com/challenges/neurips-2020-minerl-competition
[3] Flatlan trains: https://www.aicrowd.com/challenges/flatland-challenge
[4] Pommerman: https://www.pommerman.com
[5] Atari: https://youtu.be/XjsY8-P4WHM?t=48
[6] Montezuma Revenge: https://gym.openai.com/envs/MontezumaRevenge-v0
[7] Doom: http://vizdoom.cs.put.edu.pl
[8] Character Control (PFNN): https://youtu.be/Ul0Gilv5wvY
[9] Character Control (DeepMimic) https://youtu.be/vppFvq2quQ0
ntroduction to Neural Networks or Advanced Neural Networks courses.
Python or C++ ( > 1 year).
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.