In this project, you will gain practical experience with deep neural network architectures to train AI agents in simulated game environments [1-8].
PHYRE: https://player.phyre.ai
Minecraft: https://minerl.io/
Minecraft BASALT: https://www.aicrowd.com/challenges/neurips-2022-minerl-basalt-competition
Flatlan trains: https://www.aicrowd.com/challenges/flatland-challenge
Pommerman: https://www.pommerman.com
CARLA: https://carla.org/
In case the proposal would not attract enough students for a team project, I'd adapt it into an individual project or a project for two students (tandem project)
Required skills
- Theoretical and practical experience with Deep Learning
- Python experience > 1 year.
Frequency | Weekday | Time | Format / Place | Period | |
---|---|---|---|---|---|
block | Block | 03.04.-14.07.2023 |
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.