VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Reinforcement Learning for Understanding and Modeling Human Behavior
Last Updated: 2026-07-21 00:35:18
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.