Physics Department, TUM | Course 0000003356 in WS 2020/1

General Data

Course Type	lecture with integrated exercises
Semester Weekly Hours	4 SWS
Organisational Unit	Informatics 6 - Chair of Robotics, Artificial Intelligence and Real-time Systems (Prof. Knoll)
Lecturers	Berthold Bäuml
Dates

Assignment to Modules

IN2349: Weiterführendes Deep Learning für die Robotik / Advanced Deep Learning for Robotics
This module is included in the following catalogs:
- Focus Area Bio-Sensors in M.Sc. Biomedical Engineering and Medical Physics

Further Information

Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.

additional remarks	This course is 2V + 2P, the practical part always takes place directly after the lecture. The course will be given by B. Bäuml. Details about the course, esp. about its special digital form for this semester, will be given on the course webpage: https://bbaeuml.github.io/tum-adlr/ This is the advanced deep learning lecture with a specific focus on Robotics and deep reinforcement learning (including a guest lecture from DeepMind). For the semester long project in the practical part, for each student $1000 credits in the Google Cloud are provided. Taking the “Introduction to Deep Learning” course is expected. 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. Deep Reinforcement Learning I  MDPs, Q-iteration, Bellman equation, deep Q-learning, example: Atari-games 8. Deep Reinforcement Learning II  policy gradients, REINFORCE, actor-critic algorithm, TRPO, PPO, robotic applications 9. Deep Reinforcement Learning III  advanced methods: DDPG, soft Q-learning, soft actor-critic (SAC), robotic applications 10. Deep Reinforcement Learning IV  model-based DRL, MCTS + learned heuristics, AlphaZero, model learning, PDDM, robotics applications 11. Guest Lecture from DeepMind  Recent Developments in Deep Reinforcement Learning for Robotics
Links	Course documents E-Learning course (e. g. Moodle) Additional information TUMonline entry

additional remarks

This course is 2V + 2P, the practical part always takes place directly after the lecture. The course will be given by B. Bäuml. Details about the course, esp. about its special digital form for this semester, will be given on the course webpage: https://bbaeuml.github.io/tum-adlr/ This is the advanced deep learning lecture with a specific focus on Robotics and deep reinforcement learning (including a guest lecture from DeepMind). For the semester long project in the practical part, for each student $1000 credits in the Google Cloud are provided. Taking the “Introduction to Deep Learning” course is expected. 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. Deep Reinforcement Learning I  MDPs, Q-iteration, Bellman equation, deep Q-learning, example: Atari-games 8. Deep Reinforcement Learning II  policy gradients, REINFORCE, actor-critic algorithm, TRPO, PPO, robotic applications 9. Deep Reinforcement Learning III  advanced methods: DDPG, soft Q-learning, soft actor-critic (SAC), robotic applications 10. Deep Reinforcement Learning IV  model-based DRL, MCTS + learned heuristics, AlphaZero, model learning, PDDM, robotics applications 11. Guest Lecture from DeepMind  Recent Developments in Deep Reinforcement Learning for Robotics

Links

Course documents
E-Learning course (e. g. Moodle)
Additional information
TUMonline entry

Equivalent Courses (e. g. in other semesters)

Semester	Title	Lecturers	Dates
WS 2023/4	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B.
SS 2023	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B. Responsible/Coordination: Burschka, D.	Thu, 12:00–14:00, MI HS2
WS 2022/3	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B.
SS 2022	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B. Responsible/Coordination: Burschka, D.	Thu, 12:00–14:00, MI HS2
WS 2021/2	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B.	Thu, 12:00–15:30, virtuell Thu, 12:00–15:30, virtuell
SS 2021	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B. Burschka, D.
SS 2020	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B.
SS 2019	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B. Burschka, D.
SS 2018	Advanced Deep Learning for Robotics (IN2349)	Bäuml, B. Responsible/Coordination: Burschka, D.
SS 2017	Deep Learning in Robotics (IN2349)	Bäuml, B. Responsible/Coordination: Burschka, D.

Advanced Deep Learning for Robotics (IN2349)

Course 0000003356 in WS 2020/1

General Data

Assignment to Modules

Further Information

Equivalent Courses (e. g. in other semesters)