Universität Osnabrück

Forschungsstelle Data Science


Navigation und Suche der Universität Osnabrück


Hauptinhalt

Topinformationen

Veranstaltungen des kommenden Semesters

Deep reinforcement learning

8.3487

Dozenten

Beschreibung

The course is co-taught by Leon Schmid.

The course 'Deep Reinforcement Learning' teaches students (1) Basics of Reinforcement Learning (~Chapter 1-7 of 'Reinforcement Learning: An Introduction' by Barto&Sutton), (2) covers all important and major (recent) algorithms that combine Reinforcement Learning with Deep Learning for function approximation (including REINFORCE, A2C, A3C, TRPO, PPO, DDPG, TD3, SAC), (3) provides an overview over some major topics of current DRL research and applications, including topics like MARL, Language Emergence, Distributed RL, GamePlay, World Models, etc, and finally (4) accompanies students on creating their own DRL project. The course is graded based on an exam and the final project, furthermore 4 successful homework submissions are required.

Weitere Angaben

Ort: 66/E33: Mo. 12:00 - 16:00 (11x), 32/110: Mo. 16:15 - 17:45 (10x), 02/E04: Mi. 12:15 - 13:45 (12x), 94/E01 - E-Prüf-Raum: Montag, 19.06.2023 12:00 - 16:00, 94/E03 - E-Prüf-Raum: Montag, 19.06.2023 12:00 - 16:00, 94/E06 - E-Prüf-Raum: Montag, 19.06.2023 12:00 - 16:00
Zeiten: Mo. 12:00 - 16:00 (wöchentlich) - Flipped Classroom (12.15 - 13.45) // QnA (14.15 - 15.45), Ort: 66/E33, Mo. 16:15 - 17:45 (wöchentlich) - QnA, Ort: 32/110, Mi. 12:15 - 13:45 (wöchentlich) - QnA, Ort: 02/E04, Termine am Montag, 19.06.2023 12:00 - 16:00, Ort: 94/E01 - E-Prüf-Raum, 94/E03 - E-Prüf-Raum, 94/E06 - E-Prüf-Raum
Erster Termin: Montag, 17.04.2023 12:00 - 16:00, Ort: 66/E33
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)

Studienbereiche

  • Cognitive Science > Bachelor-Programm
  • Cognitive Science > Master-Programm