Yannick Metz

I am a 4th PhD student working on Human-AI Communcation and Reinforcement Learning from Human Feedback.

Research Interest: Reinforcement Learning from Human Feedback, Human-AI Interaction, Explainable AI, Visual Analytics

I am a 4th PhD student at the University of Konstanz & IVIA Lab at ETH Zurich, advised by Prof. Daniel Keim and Prof. Mennatalah El-Assady. I do research on Human-AI Communication, combining reinforcement learning from human feedback, interactive visualizations for explainability, and uncertainty in RL.

My Research

My main research aim is the improvement of bi-directional communication between humans and AI agents for effective learning and alignment. In particular, I focus on the following topics:

  • Wideining the space of human feedback for RL: Going beyond preference learning, and towards diverse, expressive, contextual feedback.
  • Reinforcement Learning from Human Feedback: Integrating different feedback types into the reward learning pipeline.
  • Interactive Visualizations for Explainability: Understanding RL agent behavior allows for better feedback and more trustworthy interactions.
  • Uncertainty in Reinforcement Learning: Measuring an agents uncertainty is crucial for effective human-ai communcation.

Publications

[1] Yannick Metz, David Lindner, Raphaël Baur, Mennatallah El-Assady Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework
ArXiv Preprint, Survey Paper, 2024

[ArXiv]  

[2] Yannick Metz, David Lindner, Raphaël Baur, Daniel A. Keim, Mennatallah El-Assady RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback
ICML2023 Interactive Learning from Implicit Human Feedback Workshop, Full Paper, 2023

[ArXiv]   [Website]   [Demo]  

[3] Yannick Metz, Eugene Bykovets, Lucas Joos, Daniel A. Keim, Mennatallah El-Assady Visitor: Visual interactive state sequence exploration for reinforcement learning
Full Paper (Eurovis), Computer Graphics Forum, 2023

[Paper]  

[4] Yannick Metz, Udo Schlegel, Daniel Seebacher, Mennatallah El-Assady, Daniel A. Keim A Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analytics
Short Paper, EuroVA, 2022

[Paper]  

[5] Eugene Bykovets, Yannick Metz, Mennatallah El-Assady, Daniel A. Keim, Joachim M Buhmann How to Enable Uncertainty Estimation in Proximal Policy Optimization
ArXiv Preprint, 2022

[ArXiv]  

[6] Dirk Streeb, Yannick Metz, Udo Schlegel, Bruno Schneider, Mennatallah El-Assady, Hansj{"o}rg Neth, Min Chen, Daniel A. Keim Task-based visual interactive modeling: Decision trees and rule-based classifiers
IEEE Transactions on Visualization and Computer Graphics, 2021

[Paper]  

[7] Yannick Metz, Dennis Ackermann, Daniel A. Keim, Maximilian T Fischer Interactive Public Transport Infrastructure Analysis through Mobility Profiles: Making the Mobility Transition Transparent
Visualization in Data Science (VDS at IEEE VIS), 2024

[Paper]  

[8] Maximilian C Hartmann, Moritz Schott, Alishiba Dsouza, Yannick Metz, Michele Volpi, Ross S Purves A text and image analysis workflow using citizen science data to extract relevant social media records: Combining red kite observations from Flickr, eBird and iNaturalist
Ecological Informatics

[Paper]  

[9] Mennatallah El-Assady, Rebecca Kehlbeck, Yannick Metz, Udo Schlegel, Rita Sevastjanova, Fabian Sperrle, Thilo Spinner Semantic color mapping: A pipeline for assigning meaningful colors to text
2022 IEEE 4th Workshop on Visualization Guidelines in Research, Design, and Education (VisGuides)

[Paper]  

[10] Yannick Metz Effective Imitation and Reinforcement Learning Through Visual Analytics
Masters Thesis

[PDF]  

[11] Yannick Metz Evaluating Concept Attributions for the Interpretability of Deep Neural Networks
Bachelor Thesis

[PDF]  

Teaching

  • TA: Seminar: Data Visualization and Analysis (UKON) - WS 2024/25
  • TA: Data Mining: Basic Concepts (UKON) - WS 2022/23 and WS 2023/24
  • TA: Data Visualization (UKON) - SS 2023
  • TA: Natural Language Processing/Document Analysis (UKON) - SS 2022
  • TA: Programming Course: Object-Oriented Programming (UKON) - WS 2021/22 and SS 2024

Education

I have a M.Sc. and B.Sc. in Computer Science from the University of Konstanz, Germany. I have also studien abroad in Uppsala, Sweden for a year. I focused During my studies, i have worked for 2 years as a working student Airbus Defence and Space in Immenstaad, Germany. I have also worked as a student research assistant at the University of Konstanz.