PEM_RL in other semesters:
SS23 WS2122 WS2021

Practical Course Development of Media Systems: Reinforcement Learning

Lecturers: Yannick Weiss, Jesse Grootjen, Florian Bemmann Professor in Charge: Prof. Sven Mayer
Hours per week: 4
ECTS-Credits: 6
Modul: Master P5.0.2 oder P5.0.4: Gruppenpraktikum zu fortgeschrittenen Themen der Informatik I oder Informatik II
After consultation with the examination board, credit for P2, P3 or P6 (advanced topics for Master) also possible

News
Contents
- Inspiring Papers
Other lectures on the topic
Schedule
Location
Application

News

09.05.2023: Please sign up for our Moodle course SS23 PEM RL. The password will be provided in the first session.
08.02.2023: This page is still under development, all content may be subject to change.

We work on solutions for the use of Machine Learning for Media Systems. During the first half we will learn some basics and consolidate it in small exercises using Python and Unity. In the second hald, you should implement your own ideas and present it as a prototype. The ideas will be implemented and presented as a prototype.

Inspiring Papers

Authors	Venue	Title
Yonghao Long, Wang Wei, Tao Huang, Yuehao Wang and Qi Dou	Submitted to ICRA 2023	Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning
Gupta, T., & Gori, J.	CHI EA 2023	Modeling reciprocal adaptation in HCI: a Multi-Agent Reinforcement Learning Approach
Ahadi-Sarkani, Armand and Elmalaki, Salma	CPHS 2021	ADAS-RL: Adaptive Vector Scaling Reinforcement Learning For Human-in-the-Loop Lane Departure Warning
Ã“scar PÃ©rezâ€‘Gil et al.	Multimedia Tools and Applications 2022	Deep reinforcement learning based control for Autonomous Vehicles in CARLA
Kashyap Todi, Gilles Bailly, Luis Leiva, and Antti Oulasvirta. 2021.	CHI 2021	Adapting User Interfaces with Model-based Reinforcement Learning
Saurav Singh, Jamison Heard	HRI 2022	Human-Aware Reinforcement Learning for Adaptive Human Robot Teaming
Jonas Tjomsland, Ali Shafti, A. Aldo Faisal	NeurIPS 2019	Human-Robot Collaboration via Deep Reinforcement Learning of Real-World Interactions
Chengxi Li et al.	AAMAS 2018	An Ar-Assisted Deep Reinforcement Learning-Based Approach Towards Mutual-Cognitive Safe Human-Robot Interaction
Hannes Ritschel	AAMAS 2018	Socially-Aware Reinforcement Learning for Personalized Human-Robot Interaction
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf	WWW 2023	Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics
Mojtaba Taherisadr, Stelios Andrew Stavroulakis, Salma Elmalaki	IoTDI 2023	adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential Decision Making Human-in-the-Loop Systems

Schedule

Please note that due to the engaging nature of the group projects, students have to spend more than the allocated time on the development of their prototypes. This is especially true for the group project implementation scheduled during the lecture break.

Date	Time	Topic
09.05.2023	16:00-18:00	Lecture 1: Introduction & Project Brainstorming
23.05.2023	16:00-18:00	Lecture 2: 90-sec Paper Presentation
06.06.2023	16:00-18:00	Lecture 3: TBA
20.06.2023	16:00-18:00	Lecture 4: Project Ideation & Group Formation
04.07.2023	16:00-18:00	Lecture 5: TBA
18.07.2023	16:00-18:00	Lecture 6: TBA
28.08.2023	09:00-17:00	Work on the projects
29.08.2023	09:00-17:00	Work on the projects
30.08.2023	09:00-17:00	Work on the projects
31.08.2023	09:00-17:00	Work on the projects
01.09.2023	09:00-12:00	Work on the projects
01.09.2023	12:00-17:00	Final presentations

Location

The course takes at Location: Frauenlobstr. 7a, Room 357

Application

Interested students can apply for this practical course via Uni2Work .

The applications should include the following information:

Describe relevant expertise, for example from previous courses, jobs and other projects, if any, that demonstrate your skills.
If you already have a project idea that you would like to implement in this course, please sketch it out briefly.