Course details


Deep Reinforcement Learning

SS 2022 Prof. Dr. Gordon Pipa, Dr. Elia Bruni Hybrid
B.Sc modules:
CS-BWP-AI - Artificial Intelligence
CS-BWP-MCS - Methods of Cognitive Science
CS-BWP-NI - Neuroinformatics
KOGW-WPM-KI - Artificial Intelligence
KOGW-WPM-NI - Neuroinformatics
M.Sc modules:
CC-MWP-AI - Artificial Intelligence
CC-MWP-NI - Neuroinformatics
CS-MWP-AI - Artificial Intelligence
CS-MWP-NI - Neuroinformatics

CS-BW - Bachelor elective course
Doctorate program

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.