====== Projektgruppe 642 (Sommersemester 2021) ======

===  Verteiltes Deep Reinforcement Learning System zum Trainieren von Game AI === 

  * Veranstalter:  [[https://ls11-www.cs.tu-dortmund.de/people/rudolph/|Prof. Dr. Günter Rudolph]] [[https://ls11-www.cs.tu-dortmund.de/staff/pleines|M.Sc. Marco Pleines]] [[https://ls11-www.cs.tu-dortmund.de/staff/kalkreuth|M.Sc. Roman Kalkreuth]]

=== Regelmäßiger betreuter Zeitraum ===

Mittwochs 11 - 12 Uhr

Discord

Ansonsten je nach Bedarf Termine mit den Betreuern vereinbaren.

=== Deadnline Abschlussbericht ===

31.03.2022

=== PG Richtlinien und Modulhandbuch ===

[[https://www.cs.tu-dortmund.de/nps/de/Studium/Ordnungen_Handbuecher_Beschluesse/Modulhandbuecher/Master_Inf/Pflichtveranstaltungen/INF-MSc-101.pdf|Modulhandbuch]]

[[https://www.cs.tu-dortmund.de/nps/de/Studium/besondere_Lehrveranstaltungen/Projektgruppen/Rechtliches/PGRichtlinien/PGR_2012__2012_10_24.pdf|PG Richtlinien]]



=== Seminartermine ===

^ Thema ^  Datum  ^  Uhrzeit  ^  Platform  ^
| Rainbow DQN |  15.04.21 | 14:00 Uhr | Zoom |
| Soft Actor-Critic |  22.04.21 | 14:00 Uhr | ::: |
| Proximal Policy Optimization |  29.04.21 | 14:00 Uhr | ::: |
| Never Give Up |  06.05.21 | 14:00 Uhr | ::: |


=== Folien ===

^  Nr.  ^  Thema  ^  Download  ^  
| 1 | Kick-Off Meeting | {{ :teaching:pg642-kick-off.pdf |PG642-Kick-Off.pdf}} | 
| 2 | Projektmanagement Workshop Teil I | {{ :teaching:pg642:pg642-projektmanagement-workshop-1.pdf |PG642-Projektmanagement-Workshop-1.pdf}} | 
| 2 | Projektmanagement Workshop Teil II | {{ :teaching:pg642:projektmanagement_workshop_teil2.pdf |PG642-Projektmanagement-Workshop-2.pdf}} | 
| 3 | Projektmanagement Workshop Teil III | {{ :teaching:pg642:projektmanagement_workshop_teil3.pdf |PG642-Projektmanagement-Workshop-3.pdf}} | 


=== Praktikum ===

^  Nr.  ^  Thema  ^  Download  ^  
| 1 | DRL Umwelten |  {{ :teaching:pg642:praktikum_01_folien.pdf |Praktikum_01_Folien.pdf}} {{ :teaching:pg642:praktikum_01_aufgaben.pdf |Praktikum_01_Aufgaben.pdf}} | 
| 2 & 3 | Experimente, LiDo 3 |  {{ :teaching:pg642:praktikum_02_folien.pdf |Praktikum_02_Folien.pdf}} {{ :teaching:pg642:praktikum_02_aufgaben.pdf |Praktikum_02_Aufgaben.pdf}} {{https://drive.google.com/file/d/1QTX4DUYCqP2AN6BfejIukoO80qUerWbq/view?usp=sharing|Datenpaket}} {{https://colab.research.google.com/drive/1K5Pq29oTyoHgJp2rsZ7rNN0N9kbn7Bq9?usp=sharing|Google Colab}}|
| 4 | Testing, Debugging | {{ :teaching:pg642:praktikum_03.pdf |}}|




=== Literatur ===

== Bücher ==

  *  R. S. Sutton and A. G. Barto :  "Reinforcement Learning: An Introduction", MIT Press, Cambridge, 2018 (ISBN:  9780262039246)
  *  G. N. Yannakakis and J. Togelius :  "Artificial Intelligence and Games", Springer, 2018 (ISBN: 9783319635194) 
  *  M. Lapan:  "Deep Reinforcement Learning Hands-On", Packt Publishing, 2018 (ISBN: 9781788834247) 
  *  L. Graesser and W. L. Keng: "Foundations of Deep Reinforcement Learning",  Addison-Wesley Professional, 2019 (ISBN: 9780135172490) 
  * M. Morales: "grokking Deep Reinforcement Learning", Manning Publications Co., 2020 (ISBN: 9781617295454)

== Paper/Tutorials ==

  *  V. Mnih et al., “Human-level control through deep reinforcement learning”, Nat., vol. 518, no. 7540, pp. 529-533, 2015 K.Cobbe et al., “Leveraging procedural generation to benchmark reinforcement learning”, CoRR,vol. abs/1912.01588, 2019.
  * A. Juliani et al., “Obstacle tower: A generalization challenge in vision, control, and planning”, in Proceedings IJCAI 2019, Macao, China (S. Kraus, ed.), pp. 2684-2691, ijcai.org, 2019.
  * O. Vinyals et al., “Grandmaster level in starcraft II using multi-agent reinforcement learning”, Nat., vol. 575, no. 7782, pp. 350-354, 2019.
  * C. Berner et al., “Dota 2 with large scale deep reinforcement learning”, CoRR, vol. abs/ 1912.06680, 2019.
  * C. Hidber, “Reinforcement Learning: a gentle Introduction and industrial Application”, aufgerufen über https://youtu.b/3RjSanoNIlk am 14.12.2020, 2019.
  * M. Andrychowicz et al., “Learning dexterous in-hand manipulation”, Int. J. Robotics Res., vol. 39, no. 1, 2020.
  * M. G. Bellemare et al., “Autonomous navigation of stratospheric balloons using reinforcement learning”, Nat. vol. 588, pp.77-82, 2020.