Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
rudolph:cig_new [2021-10-19 10:44]
Marco Pleines [Games for Computational Intelligence Research]
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:​nicolas_fischoeder|Nicolas Fischöder]]
  
 ===== Games for Computational Intelligence Research ===== ===== Games for Computational Intelligence Research =====
Line 90: Line 91:
  
   * [[https://​pypi.org/​project/​catanatron/​|Catan]]   * [[https://​pypi.org/​project/​catanatron/​|Catan]]
 +
   * [[https://​sites.google.com/​view/​arena-unity/​home/​learning-environments|Arena]]   * [[https://​sites.google.com/​view/​arena-unity/​home/​learning-environments|Arena]]
 ===== Publications ===== ===== Publications =====
Line 125: Line 127:
 ===== Project Groups ===== ===== Project Groups =====
  
-=== PG 511 === +=== PG 642: Verteiltes Deep Reinforcement Learning System zum Trainieren von Game AI ===
- +
-=== PG 529 ===+
  
-== Stragotiator ==+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. 
 +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 =====
 
Last modified: 2022-05-09 13:12 by Marco Pleines
DokuWikiRSS-Feed