Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
rudolph:cig_new [2021-10-27 14:51] Marco Pleines |
rudolph:cig_new [2021-10-27 15:07] Marco Pleines [Project Groups] |
||
---|---|---|---|
Line 27: | Line 27: | ||
* [[staff:rudolph|Prof. Dr. Günter Rudolph]] | * [[staff:rudolph|Prof. Dr. Günter Rudolph]] | ||
* [[staff:pleines|Marco Pleines]] | * [[staff:pleines|Marco Pleines]] | ||
- | * [[staff:fischoeder_nicolas|Nicolas Fischöder]] | + | * [[staff:nicolas_fischoeder|Nicolas Fischöder]] |
===== Games for Computational Intelligence Research ===== | ===== Games for Computational Intelligence Research ===== | ||
Line 127: | Line 127: | ||
===== Project Groups ===== | ===== Project Groups ===== | ||
- | === PG 511 === | + | === PG 642: Verteiltes Deep Reinforcement Learning System zum Trainieren von Game AI === |
- | === PG 529 === | + | The goal of this project group is to train agents to play Rocket League using a distributed Deep Reinforcement Learning system. |
- | + | Training directly on Rocket League comes with many issues. Therefore, the game is reimplemented in Unity. | |
- | == Stragotiator == | + | This raises the challenge of transferring the learned behavior in Unity to Rocket League, which is called a sim-to-sim transfer. |
+ | As this project is still ongoing, there are no outcomes to be presented yet. | ||
===== Fachprojekte (technical projects) Digital Entertainment Technologies ===== | ===== Fachprojekte (technical projects) Digital Entertainment Technologies ===== |