Philipp Altmann

Philipp Altmann Philipp Altmann

Education

[Expand]
  • Ph.D. Computer Science, LMU Munich (2020 – present)
  • M.Sc. Computer Science, LMU Munich (2018 – 2020)
  • B.Sc. Media Informatics, LMU Munich (2014 – 2018)
  • Abitur, Otfried-Preußler-Gymnasium Pullach (2006 – 2014)

    • Professional Experience

    [Expand]
  • Research Associate, LMU Munich (2020 – present)
  • Research Assistant, LMU Munich (2019 – 2020)
  • Web Developer, Polyteia, Munich (2017 – 2018)
  • Working Student, Ray Sono, Munich (2015 – 2017)

    • Research Interests

    [Collapse]
  • Collective Intelligence — ExplorationRobustnessAlignment (2021 – present)
  • Reinforcement Learning and Agentic Systems (2017 – present)
  • Alignment and Incentive Design in Multi-Agent Systems [C45,C42,C39,J1,C9,C4]
  • Representation and Reward Modeling in RL [J2,C11,C12,C8,C2]
  • Interpretable and Human-Aligned RL [J3,C30,C29]
  • Applied RL and Agentic Systems [C35,C27,C31,C24,C13]
  • Evolutionary Optimization and Processes (2017 – present)
  • Surrogate-Assisted and Genetic Search in Learning Systems [J3,C30,C14,C33,C1]
  • Evolutionary Selection and Replication in Neural Systems [C36,C28,C18,C15]
  • Quantum Machine Learning (2020 – present)

    • Selected Publications

    [Expand]
  • Publication Statistics (as of February 2026): 343 Citations, h-Index: 10, i10-Index: 12

    • Honors and Awards

    [Expand]
  • Best Poster Award for our paper “Finding Strong Lottery Ticket Networks with Genetic Algorithms” and invitation to submit an extended version to Studies in Computational Intelligence. (IJCCI 2024)
  • Paper Selection Invitation to submit an extended version of our paper “REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning” to Springer Nature Computer Science. (IJCCI 2024)
  • Paper Selection Invitation to submit an extended version of our paper “Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures” to Springer LNAI. (ICAART 2024)
  • Paper Selection Invitation to submit an extended version of our paper “Improving Parameter Training for VQEs by Sequential Hamiltonian Assembly” to Springer LNAI. (ICAART 2024)
  • Paper Selection Invitation to submit an extended version of our paper “Multi-Agent Quantum Reinforcement Learning Using Evolutionary Optimization” to Springer LNAI. (ICAART 2024)
  • Paper Selection Invitation to submit an extended version of our paper “DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training” to Neural Computing and Applications. (ALA@AAMAS2023)
  • Premier Paper Invitation to submit an extended version of our paper “Emergent Cooperation from Mutual Acknowledgment Exchange” to Autonomous Agents and Multi-Agent Systems. (AAMAS 2022)
  • Highlight Paper Recognition of our AAMAS 2022 paper “Emergent Cooperation from Mutual Acknowledgment Exchange” at the IJCAI 2022 Workshop on Ad Hoc Teamwork. (WAHT@IJCAI 2022)
  • Best Poster Award for our paper “Finding Strong Lottery Ticket Networks with Genetic Algorithms” and invitation to submit an extended version to Studies in Computational Intelligence. (IJCCI 2024)
  • Paper Selection Invitation to submit an extended version of our paper “REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning” to Springer Nature Computer Science. (IJCCI 2024)
  • Paper Selection Invitation to submit an extended version of our paper “DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training” to Neural Computing and Applications. (ALA@AAMAS2023)
  • Premier Paper Invitation to submit an extended version of our paper “Emergent Cooperation from Mutual Acknowledgment Exchange” to Autonomous Agents and Multi-Agent Systems. (AAMAS 2022)
  • Highlight Paper Recognition of our AAMAS 2022 paper “Emergent Cooperation from Mutual Acknowledgment Exchange” at the IJCAI 2022 Workshop on Ad Hoc Teamwork. (WAHT@IJCAI 2022)

    • Project Experience

    [Collapse]
  • Munich Quantum Valley (MQV) (2021 – present)
  • Promote quantum science and technologies to develop and operate competitive quantum computers.
  • Funding: Bavarian state government with funds from the Hightech Agenda Bayern.
  • Partner: BAdW, DLR, FhG, FAU, MPG, TUM. Role: Principal Investigator.
  • AI-Fusion: Evaluation of Emergence in Distributed AI Systems (2022 – 2024)
  • Transferring safe intelligence from research to application.
  • Funding: Bavarian Ministry of Economic Affairs, Regional Development, and Energy.
  • Partner: Fraunhofer Institute for Cognitive Systems.
  • QAR-Lab: Quantum Applications and Research Laboratory (2021 – 2022)
  • Building a Bavarian ecosystem for quantum computing and user expertise.
  • Funding: Bavarian Ministry of Economic Affairs, Regional Development, and Energy.
  • PlanQK: Platform and Ecosystem for Quantum-Assisted Artificial Intelligence (2020 – 2022)
  • Create a technical basis for knowledge and technology exchange on quantum-assisted AI.
  • Funding: Federal Ministry for Economic Affairs and Energy.
  • InnoMI – Innovation Center Mobile Internet (2020 – 2022)
  • Research on innovative mobile and distributed systems.
  • Funding: Bavarian Ministry of Economic Affairs, Regional Development, and Energy.

    • Teaching Experience

    [Collapse]
  • Working Group Artificial Intelligence (2023 – present)
  • Weekly exchange and supervision of research projects across computational intelligence, RL, MAS, and QML.
  • Voluntary additional module, supervision of 8–12 students per semester supporting their thesis projects.
  • Practical Course Autonomous Systems (2022 – 2025)
  • Lectures on RL and autonomous decision-making (policy optimization, reward design, exploration strategies).
  • Supervised project-based development of continuous-control and embodied learning systems evaluated under uncertainty, including Unity-based autonomous driving agents and MuJoCo-based robotic grasping environments.
  • Guided 16–24 students per semester (teams of 3–5) in designing, training, and evaluating autonomous agents, with emphasis on scalable experimentation, modular environment design, and robust performance assessment.
  • Practical Course Affective Computing (2021 – present)
  • Hands-on course on multimodal and human-centered machine learning (vision, speech, emotion, and physiological signals).
  • Supervised 100+ students across 30+ projects developing end-to-end affect-aware systems, including multimodal sentiment extraction, emotion-conditioned generation, recommender systems, assistive technology, and healthcare applications.
  • Guided students in integrating deep learning and foundation models (LLMs/VLMs) into agentic and multimodal pipelines (e.g., zero-shot music recommendation, empathetic voicebots, intention prediction, and real-time safety monitoring).
  • Thesis Supervision (11 master theses, 17 bachelor theses, [Full List]) (2021 – present)
  • Topics include reinforcement learning from preferences and curriculum design; multi-objective and diversity-driven policy optimization; cooperative MARL and meta-reward design; LLM-based agent optimization and evolutionary prompt search; vision-based robotic grasping and embodied reinforcement learning; and hybrid quantum machine learning architectures.

    • Volunteer Work and Activities

    [Expand]
  • Head of Office, Digitale Stadt München e.V. (2021 – present)
  • Festival Booking and Artist Relations, Kulturspektakel Gauting e.V. (2017 – present)
  • Bartender for events and concerts (since 2019 in managerial position) (2015 – 2024)

    • Professional Services

    [Expand]
  • Program Committee: AAAI, ACII, ALA, IJCAI, GECCO, QAIO
  • Reviewer: Data Mining and Knowledge Discovery, ICLR, ICML, Nature Communications Physics, Neural Computing and Applications, NeurIPS, RLC, SN Computer Science
  • Reviewer, Data Mining and Knowledge Discovery (2026)
  • Reviewer, 14th International Conference on Learning Representations (ICLR 2026)
  • Program Committee, 40th AAAI Conference on Artificial Intelligence (AAAI 2026)
  • Reviewer, Nature Communications Physics (since 2025)
  • Reviewer, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
  • Program Committee, 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
  • Reviewer, 42nd International Conference on Machine Learning (ICML 2025)
  • Program Committee, 17th Workshop on Adaptive and Learning Agents (ALA 2025)
  • Program Committee, 27th Genetic and Evolutionary Computation Conference (GECCO 2025)
  • Program Committee, 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
  • Program Committee, 1st Quantum Artificial Intelligence and Optimization (QAIO2025)
  • Reviewer, 13th International Conference on Learning Representations (ICLR 2025)
  • Program Committee, 39th AAAI Conference on Artificial Intelligence (AAAI 2025)
  • Reviewer, 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
  • Reviewer, 1st Reinforcement Learning Conference (RLC 2024)
  • Program Committee, 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024)
  • Reviewer, 41st International Conference on Machine Learning (ICML 2024)
  • Reviewer, Neural Computing and Applications (since 2024)
  • Reviewer, Springer Nature Computer Science (since 2024)
  • Reviewer, 12th International Conference on Learning Representations (ICLR 2024)
  • Reviewer, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
  • Program Committee, 31st International Conference on Affective Computing and Intelligent Interaction (ACII 2023)

    • Talks

    [Expand]
  • “Surrogate Modelling for Collective Intelligence,” Doctoral Seminar, Chair of Artificial Intelligence and Machine Learning, LMU Munich. (2025)
  • “Distributional Shift Robust Reinforcement Learning,” #WeAreExperts Tech Talk @ Fraunhofer IKS. (2024)
  • “Meta Heuristics for Quantum Circuit Design,” Munich Quantum Software Stack Exchange Meeting. (2024)
  • “REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning,” virtual paper presentation at the 16th International Conference on Evolutionary Computation Theory and Applications at IJCCI. (2024)
  • “Emergence in Multi-Agent Systems - A Safety Perspective,” oral paper presentation at the Rigorous Engineering of Collective Adaptive Systems (REOCAS) track at ISoLA. (2024)
  • “SEGym: Optimizing Large Language Model Assisted Software Engineering Agents with Reinforcement Learning,” oral paper presentation at the AI Assisted Programming track at AISoLA. (2024)
  • “CROP: Towards Distributional-Shift Robust Reinforcement Learning Using Compact Reshaped Observation Processing,” virtual paper presentation at the main track at IJCAI. (2023)
  • “DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training,” oral paper presentation at the 15th Adaptive and Learning Agents Workshop at AAMAS. (2023)

    • Skills

    [Collapse]     PythonC++GoJavascriptPyTorchTensorFlowNumpyGymnasiumMuJoCoDockerGitLLMsLaTeXUnityBlenderIllustratorExperiment DesignScientific WritingData AnalysisProject ManagementSupervision & MentoringTeachingCross-Disciplinary CollaborationPeer Reviewing
    , ,, in , , in vol. no. , pp. , . . [Code] [PDF] [Preprint]