Advanced Deep Learning for Robotics
This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.
IN2349 is a semester module in English language at Master’s level which is offered every semester.
This Module is included in the following catalogues within the study programs in physics.
- Focus Area Bio-Sensors in M.Sc. Biomedical Engineering and Medical Physics
|Total workload||Contact hours||Credits (ECTS)|
|180 h||60 h||6 CP|
Content, Learning Outcome and Preconditions
1. Introduction & Recap of Deep Learning
2. Advanced Network Architectures & Recursive Neural Networks (LSTMs)
3. Hyperparameter & Architecture Search
Bayesian optimization, network architecture search (NAS)
4. Adversarial Samples & Adversarial Training
5. Bayesian Deep Learning
Bayesian learning, variational inference, Monte Carlo dropout method
6. Generative Models: VAEs & GANs
variational auto-encoders, generative neural networks (WGAN-GP)
7. Data Efficient Learning: Transfer & Semi-Supervised Learning
8. Deep Reinforcement Learning I
MDPs, Q-iteration, Bellman equation, deep Q-learning, example: Atari-games
9. Deep Reinforcement Learning II
policy gradients, REINFORCE, actor-critic algorithm, TRPO, PPO, robotic applications
10. Deep Reinforcement Learning III
advanced methods: DDPG, soft Q-learning, soft actor-critic (SAC), robotic applications
11. Deep Reinforcement Learning IV
model-based DRL, MCTS + learned heuristics, AlphaZero, model learning, PDDM, robotics
12. Guest Lecture from DeepMind
Recent Developments in Deep Reinforcement Learning for Robotics
MA0901 Linear Algebra for Informatics
IN2346 Introduction to Deep Learning (expert knowledge required!)
Courses, Learning and Teaching Methods and Literature
Courses and Schedule
|VI||4||Advanced Deep Learning for Robotics (IN2349)||Bäuml, B.||
Learning and Teaching Methods
The practical sessions will be key, students shall get familiar with esp. Deep Reinforcement Learning through hours of training and testing. The students will do a semester-long project in teams of 2 with weekly presentations and tutoring of the projects throughout the semester. They will work with TensorFlow and OpenAI Gym and implement advanced deep reinforcement learning methods for state of the art robotic problems. For each student, $1000 credits in the Google Cloud are available via a Google Educational Grant.
Description of exams and course work
- After each practical session, the students will have to provide the written working code to the teaching assistant for evaluation.
- In the written exam (50% of the final grade), we will ask questions regarding lecture theory
- In addition, to the written exam, the results of the projects will be evaluated (50% of the final grade); we will evaluate projects on a (bi-) weekly basis including reports (33.33%), oral presentations (33.33%), and code/submissions (33.33%).
There is a possibility to take the exam in the following semester.
Current exam dates
Currently TUMonline lists the following exam dates. In addition to the general information above please refer to the current information given during the course.
|Advanced Deep Learning for Robotics|
|Fri, 2023-02-17, 14:15 till 16:15||2501
||till 2023-01-15 (cancelation of registration till 2023-02-10)|