VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

263-5910-00L 2 Credits MSC , WBZ D-INFK

Reinforcement Learning for Understanding and Modeling Human Behavior

Lecturers & Examiners: Prof. Dr. Christian Holz, Dr. Yi-Chi Liao

The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.

VVZ CR n/a

Last Updated: 2026-06-03 00:14:10

Abstract

Reinforcement learning (RL) methods have advanced, and it has the potential to offer robust policies for modeling users and guide adaptive systems. Those advancements lead to many open challenges and wide application scope. In this course, students present and discuss papers from relevant top-tier research venues to extract techniques and insights from RL research and application in HCI.

Objective

In this course, students present and discuss papers from relevant top-tier research venues to extract techniques and insights from RL research and application in Human-Computer Interaction.

Content

The objective of the seminar is for participants to collectively learn about the state-of-the-art research in Reinforcement Learning and closely related areas. This includes the ability to concisely present results of pioneering as well as state-of-the-art research. Another objective is to collectively discuss open issues in the field and developing a feeling for what constitutes research questions and outcomes in the field of technical Human-Computer Interaction.

Resources

Literature

14 papers will be provided by the lecturer and distributed in the first seminar on a first-come, first-served basis according to participants' preferences. The lecturer will also give a brief run-down across all 14 papers in a fast-forward style, covering each paper in a single-minute presentation, and outline the difficulties of each project. The schedule is fixed throughout the term with easier papers being presented earlier and more comprehensive papers presented later in the term.

Learning Materials (Links)

Main link
Information

General Information

Language: English
Levels: MSC , WBZ
Frequency: Yearly recurring

Examination

Type: graded semester performance

Students individually read one full-paper publication, working through its content in detail and covering background literature if necessary.Students then present the approach, methodology, research question and implementation as well as the evaluation and discussion in a 20–25 min talk in front of the others. Each presenter will then lead a short discussion about the paper, which is also guided by questions posed to the audience.

Registration & Places

Max Places: 14

Course Components

Type	Title	Time & Place	Hours
seminar	Reinforcement Learning for Understanding and Modeling Human Behavior	Wed 16:15-18:00 (STD G 1)	2 h weekly