Hauptinhalt
Topinformationen
Deep reinforcement learning
8.3487
Dozenten
Beschreibung
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. The course is offered entirely in a hybrid manner, offering participation also to students from the COSMOS program.
Weitere Angaben
Ort: 66/E34: Mo. 12:00 - 14:00 (11x),
32/107: Mi. 14:00 - 16:00 (13x)
Zeiten: Mo. 12:00 - 14:00 (wöchentlich) - Lecture / Flipped Classroom, Ort: 66/E34,
Mi. 14:00 - 16:00 (wöchentlich) - Coding Support / QnA, Ort: 32/107
Erster Termin: Montag, 11.04.2022 12:00 - 14:00, Ort: 66/E34
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)
Studienbereiche
- Cognitive Science > Bachelor-Programm
- Cognitive Science > Master-Programm
- Cognitive Science > Promotionsprogramm