 |
Kyrill Schmid Lehrstuhl für Mobile und Verteilte Systeme Ludwig-Maximilians-Universität München, Institut für Informatik Oettingenstraße 67 Raum Telefon: +49 89 / 2180-9259 Fax: +49 89 / 2180-9148 Mail: kyrill.schmid@ifi.lmu.de |
Now working @ ZenAI
🎓 Forschungsgebiete
- Artificial Intelligence
- Multi-Agent Systems & Multi-Agent Learning
- Coordination & Cooperation
📚 Publikationen
2021
- Kyrill Schmid, Lenz Belzner, Robert Müller, Johannes Tochtermann and Claudia Linnhoff-Popien, „Stochastic Market Games“, accepted at IJCAI 2021
- Kyrill Schmid, Lenz Belzner, Claudia Linnhoff-Popien, „Learning to Penalize Other Learning Agents“, accepted at ALIFE 2021
- Kyrill Schmid, Robert Müller, Lenz Belzner, Johannes Tochtermann and Claudia Linnhoff-Popien, „Distributed Emergent Agreements with Deep Reinforcement Learning“, accepted at IJCNN 2021
- Robert Müller, Steffen Illium, Fabian Ritz and Kyrill Schmid, Analysis of Feature Representations for Anomalous Sound Detection, ICAART 2021. [📄arXiv]
2020
- Thomy Phan, Lenz Belzner, Kyrill Schmid, Thomas Gabor, Fabian Ritz, Sebastian Feld, and Claudia Linnhoff-Popien, „A Distributed Policy Iteration Scheme for Cooperative Multi-Agent Policy Approximation,“ Adaptive and Learning Agents Workshop (ALA) @ AAMAS 2020, 2020. [Download PDF]
- Kyrill Schmid, Lenz Belzner, Thomy Phan, Thomas Gabor, and Claudia Linnhoff-Popien, „Multi-Agent Reinforcement Learning for Bargaining under Risk and Asymmetric Information,“ in 12th International Conference on Agents and Artificial Intelligence (ICAART 2020), 2020.
2019
- Stefan Langer, Robert Müller, Claudia Linnhoff-Popien and Kyrill Schmid, „Difficulty Classification of Mountainbike Downhill Trails utilizing Deep Neural Networks“, Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Springer, 2019, pp. 270-280.[📄arXiv]
- Thomy Phan, Kyrill Schmid, Lenz Belzner, Thomas Gabor, Sebastian Feld, and Claudia Linnhoff-Popien, „Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies (Extended Abstract),“ in 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), 2019.
- Thomy Phan, Lenz Belzner, Marie Kiermeier, Markus Friedrich, Kyrill Schmid, and Claudia Linnhoff-Popien, „Memory Bounded Open-Loop Planning in Large POMDPs using Thompson Sampling,“ in 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), 2019.
2018
- Thomy Phan, Lenz Belzner, Thomas Gabor, and Kyrill Schmid, „Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation,“ in 17th Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018), 2018, pp. 730-738.
- Lenz Belzner, Kyrill Schmid, Thomy Phan, Thomas Gabor, and Martin Wirsing, „The Sharer’s Dilemma in Collective Adaptive Systems of Self-Interested Agents,“ in International Symposium on Leveraging Applications of Formal Methods (ISoLA), 2018.
- Thomas Gabor, Lenz Belzner, Thomy Phan, and Kyrill Schmid, „Preparing for the Unexpected: Diversity Improves Planning Resilience in Evolutionary Algorithms,“ in 15th IEEE International Conference on Autonomic Computing (ICAC), 2018.
- Kyrill Schmid, Lenz Belzner, Thomas Gabor, and Thomy Phan, „Action Markets in Deep Multi-Agent Reinforcement Learning,“ in Artificial Neural Networks and Machine Learning (ICANN 2018), Cham, 2018, pp. 240-249.
- Kyrill Schmid, Lenz Belzner, Marie Kiermeier, Alexander Neitz, Thomy Phan, Thomas Gabor, and Claudia Linnhoff, „Risk-Sensitivity in Simulation Based Online Planning,“ in Joint German/Austrian Conference on Artificial Intelligence (Künstliche Intelligenz), 2018, pp. 229-240.
- Markus Friedrich and Kyrill Schmid, „A Virtual Reality Multi-Sensor 3d Reconstruction System,“ in 17. GI/ITG KuVS Fachgespräch Sensornetze, 2018.
2017
- André Ebert, Kyrill Schmid, Chadly Marouane, and Claudia Linnhoff-Popien, „Automated Recognition and Difficulty Assessment of Boulder Routes,“ in 4th EAI Conference on IoT Technologies for Healthcare (HealthyIoT 2017), 2017.
📖 Abschlussarbeiten
Bei generellem Interesse an einer Abschlussarbeit an unserem Lehrstuhl oder auch in meinen Themengebieten, gerne einfach eine E-Mail schicken und zu einem Gespräch vorbeikommen. Eigene Ideen für Abschlussarbeiten sind auch jederzeit willkommen!
✅ Abgeschlossene Arbeiten
- Deep Experience Planning
- Arouse & Relax: Steuerung einer Lichtumgebung anhand von physiologischen Daten und Deep Reinforcement Learning
- Untersuchung von Hybriden Reward Architekturen zur Reduzierung eines komplexen, industriellen Problems
- DeepHR: Erkennung der Herzfrequenz aus Video-Daten mit Ende-zu-Ende Deep Learning
- Klassifizierung der Dringlichkeit von Anfragen in sprachbasierter Mensch-Maschine-Interaktion mit Hilfe von Machine Learning
- Klassifikation von Agenten in Sequentiellen Sozialen Dilemmas
- Handelnde Agenten: Untersuchung des Ricardo Modells mit Deep Multi-Agent Reinforcement Learning
