Anna Penzkofer

Institute for Visualisation and Interactive Systems, University of Stuttgart

  Pfaffenwaldring 5a, 70569 Stuttgart, Germany University of Stuttgart, SimTech Building, Room 01.033 Google Scholar

Biography

Anna Penzkofer is a PhD student in the Collaborative Artificial Intelligence group since January 2023. She holds a Bachelor’s degree in Computer Science from the University of Stuttgart and a Master’s degree in Computer Science from the Technical University Munich (TUM). She has been doing research in the group since her bachelor's degree at the University of Stuttgart in 2018. Her main research interest is in computational modelling of human behaviour, specifically in visual processing. Her research includes applications of cognitive models in Computer Vision and Reinforcement Learning.

Personal website https://apenzko.github.io/

Teaching

2024

Machine Perception and Learning (Tutor)Master

 

Fachpraktikum -- Practical Course Interactive Systems: Computational Theory of Mind and Cognition (Tutor)Master

2023

Mensch-Computer-Interaktion (Teaching Assistant)Bachelor

---

Supervision

2024

Cognitively-plausible Mental Image Representations (B.Sc.) Sawelij Mödinger

 

Neural Reasoning with Cognitively-inspired Representations (B.Sc.) Levi Otterbach+

 

Leveraging Biologically-plausible Representations for Robust and Efficient Generalization in Reinforcement Learning (M.Sc.) Nan Jiang*

2023

Evaluation of Different Image Representations for Reinforcement Learning Agents (M.Sc.) Jayakumar Ramasamy Sundararaj*

 

Biologically Plausible Reinforcement Learning (B.Sc.) Tobias Stegmaier

 

An Adaptive Model of Gaze-based Selection (INFOTECH Project) Jayakumar Ramasamy Sundararaj

*Co-supervised with Constantin Ruhdorfer +Co-supervised with Matteo Bortoletto

---

Open Thesis Projects

 

Cognitive Attention Guided Imitation LearningMaster

 

Prioritized Trajectory Replay with Neuro-Inspired RepresentationMaster

 

A Vector Symbolic Algebra for Language ModelsMaster

---

Publications

(Penzkofer et al., 2024; Penzkofer et al., 2024; Penzkofer et al., 2023; Ruhdorfer et al., 2024; Müller et al., 2024; Penzkofer et al., 2021)

1. 

   Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning

   Anna Penzkofer, Simon Schaefer, Florian Strohm, Mihai Bâce, Stefan Leutenegger, Andreas Bulling

   Neural Computing and Applications (NCAA), 36, pp. 1–7, 2024.

   Abstract Links BibTeX Project

   While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e., the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma’s Revenge – one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to an HRL agent that is significantly more sample efficient than previous methods.

   doi: 10.1007/s00521-024-10596-2

   Paper: penzkofer24_ncaa.pdf

   @article{penzkofer24_ncaa, author = {Penzkofer, Anna and Schaefer, Simon and Strohm, Florian and Bâce, Mihai and Leutenegger, Stefan and Bulling, Andreas}, title = {Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning}, journal = {Neural Computing and Applications (NCAA)}, year = {2024}, pages = {1--7}, doi = {10.1007/s00521-024-10596-2}, volume = {36}, issue = {} }

1. 

   VSA4VQA: Scaling A Vector Symbolic Architecture To Visual Question Answering on Natural Images

   Anna Penzkofer, Lei Shi, Andreas Bulling

   Proc. 46th Annual Meeting of the Cognitive Science Society (CogSci), 2024.

   Abstract Links BibTeX Project Oral Presentation

   While Vector Symbolic Architectures (VSAs) are promising for modelling spatial cognition, their application is currently limited to artificially generated images and simple spatial queries. We propose VSA4VQA – a novel 4D implementation of VSAs that implements a mental representation of natural images for the challenging task of Visual Question Answering (VQA). VSA4VQA is the first model to scale a VSA to complex spatial queries. Our method is based on the Semantic Pointer Architecture (SPA) to encode objects in a hyper-dimensional vector space. To encode natural images, we extend the SPA to include dimensions for object’s width and height in addition to their spatial location. To perform spatial queries we further introduce learned spatial query masks and integrate a pre-trained vision-language model for answering attribute-related questions. We evaluate our method on the GQA benchmark dataset and show that it can effectively encode natural images, achieving competitive performance to state-of-the-art deep learning methods for zero-shot VQA.

   Paper: penzkofer24_cogsci.pdf

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/VSA4VQA

   Paper Access: https://escholarship.org/uc/item/26j7v1nf.

   @inproceedings{penzkofer24_cogsci, author = {Penzkofer, Anna and Shi, Lei and Bulling, Andreas}, title = {{VSA4VQA}: {Scaling} {A} {Vector} {Symbolic} {Architecture} {To} {Visual} {Question} {Answering} on {Natural} {Images}}, booktitle = {Proc. 46th Annual Meeting of the Cognitive Science Society (CogSci)}, year = {2024}, volume = {46}, url = {https://escholarship.org/uc/item/26j7v1nf.} }
2. 

   MultiMediate’24: Multi-Domain Engagement Estimation

   Philipp Müller, Michal Balazia, Tobias Baur, Michael Dietz, Alexander Heimerl, Anna Penzkofer, Dominik Schiller, François Brémond, Jan Alexandersson, Elisabeth André, Andreas Bulling

   Proceedings of the 32nd ACM International Conference on Multimedia, pp. 11377 - 11382, 2024.

   Abstract Links BibTeX Project

   Estimating the momentary level of participant’s engagement is an important prerequisite for assistive systems that support human interactions. Previous work has addressed this task in within-domain evaluation scenarios, i.e. training and testing on the same dataset. This is in contrast to real-life scenarios where domain shifts between training and testing data frequently occur. With MultiMediate’24, we present the first challenge addressing multi-domain engagement estimation. As training data, we utilise the NOXI database of dyadic novice-expert interactions. In addition to within-domain test data, we add two new test domains. First, we introduce recordings following the NOXI protocol but covering languages that are not present in the NOXI training data. Second, we collected novel engagement annotations on the MPIIGroupInteraction dataset which consists of group discussions between three to four people. In this way, MultiMediate’24 evaluates the ability of approaches to generalise across factors such as language and cultural background, group size, task, and screen-mediated vs. face-to-face interaction. This paper describes the MultiMediate’24 challenge and presents baseline results. In addition, we discuss selected challenge solutions.

   doi: 10.1145/3664647.3689004

   Paper: mueller24_mm.pdf

   @inproceedings{mueller24_mm, author = {M{\"{u}}ller, Philipp and Balazia, Michal and Baur, Tobias and Dietz, Michael and Heimerl, Alexander and Penzkofer, Anna and Schiller, Dominik and Brémond, François and Alexandersson, Jan and André, Elisabeth and Bulling, Andreas}, title = {MultiMediate'24: Multi-Domain Engagement Estimation}, year = {2024}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, doi = {10.1145/3664647.3689004}, booktitle = {Proceedings of the 32nd ACM International Conference on Multimedia}, pages = {11377 - 11382} }

1. 

   The Overcooked Generalisation Challenge

   Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling

   arxiv:2406.17949, pp. 1-25, 2024.

   Abstract Links BibTeX Project

   We introduce the Overcooked Generalisation Challenge (OGC) - the first benchmark to study agents’ zero-shot cooperation abilities when faced with novel partners and levels in the Overcooked-AI environment. This perspective starkly contrasts a large body of previous work that has trained and evaluated cooperating agents only on the same level, failing to capture generalisation abilities required for real-world human-AI cooperation. Our challenge interfaces with state-of-the-art dual curriculum design (DCD) methods to generate auto-curricula for training general agents in Overcooked. It is the first cooperative multi-agent environment specially designed for DCD methods and, consequently, the first benchmarked with state-of-the-art methods. It is fully GPU-accelerated, built on the DCD benchmark suite minimax, and freely available under an open-source license: this https URL. We show that current DCD algorithms struggle to produce useful policies in this novel challenge, even if combined with recent network architectures that were designed for scalability and generalisability. The OGC pushes the boundaries of real-world human-AI cooperation by enabling the research community to study the impact of generalisation on cooperating agents.

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/OGC

   Paper Access: https://arxiv.org/abs/2406.17949

   @techreport{ruhdorfer2024_arxiv, title = {The Overcooked Generalisation Challenge}, author = {Ruhdorfer, Constantin and Bortoletto, Matteo and Penzkofer, Anna and Bulling, Andreas}, year = {2024}, pages = {1-25}, url = {https://arxiv.org/abs/2406.17949} }

1. 

   Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning

   Anna Penzkofer, Simon Schaefer, Florian Strohm, Mihai Bâce, Stefan Leutenegger, Andreas Bulling

   Proc. Adaptive and Learning Agents Workshop (ALA), pp. 1–7, 2023.

   Abstract Links BibTeX Project

   While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma’s Revenge – one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to a HRL agent that is significantly more sample efficient than previous methods.

   Paper: penzkofer23_ala.pdf

   @inproceedings{penzkofer23_ala, author = {Penzkofer, Anna and Schaefer, Simon and Strohm, Florian and Bâce, Mihai and Leutenegger, Stefan and Bulling, Andreas}, title = {Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning}, booktitle = {Proc. Adaptive and Learning Agents Workshop (ALA)}, year = {2023}, pages = {1--7} }

1. 

   ConAn: A Usable Tool for Multimodal Conversation Analysis

   Anna Penzkofer, Philipp Müller, Felix Bühler, Sven Mayer, Andreas Bulling

   Proc. ACM International Conference on Multimodal Interaction (ICMI), pp. 341-351, 2021.

   Abstract Links BibTeX Project

   Multimodal analysis of group behavior is a key task in human-computer interaction, as well as the social and behavioral sciences, but is often limited to more easily controllable laboratory settings or requires elaborate multi-sensor setups and time-consuming manual data annotation. We present ConAn – a usable tool to explore and automatically analyze non-verbal behavior of multiple persons during natural group conversations. In contrast to traditional multi-sensor setups, our tool only requires a single 360° camera and uses state-of-the-art computer vision methods to automatically extract behavioral indicators, such as gaze direction, facial expressions, and speaking activity. Thus, our tool allows for easy and fast deployment supporting researchers in understanding both individual behavior and group interaction dynamics, but also in quantifying user-object interactions. We illustrate the benefits of our tool on three sample use cases: general conversation analysis, assessment of collaboration quality, and impact of technology on audience behavior. Taken together, ConAn represents an important step towards democratizing automatic conversation analysis in HCI and beyond.

   doi: 10.1145/3462244.3479886

   Paper: penzkofer21_icmi.pdf

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/conan

   Video: https://www.youtube.com/watch?v=H2KfZNgx6CQ

   @inproceedings{penzkofer21_icmi, author = {Penzkofer, Anna and Müller, Philipp and Bühler, Felix and Mayer, Sven and Bulling, Andreas}, title = {ConAn: A Usable Tool for Multimodal Conversation Analysis}, booktitle = {Proc. ACM International Conference on Multimodal Interaction (ICMI)}, year = {2021}, doi = {10.1145/3462244.3479886}, pages = {341-351}, video = {https://www.youtube.com/watch?v=H2KfZNgx6CQ} }