CV

Auto-generated from _data/cv.yml — edit that file to update this page and the downloadable PDF.

Contact Information

Name Mustafa Mert Çelikok
Email celikok@imada.sdu.dk

Experience

  • 2025 - present

    Denmark

    Tenure-track Assistant Professor
    University of Southern Denmark, Department of Mathematics and Computer Science, Data Science Section
  • 2026 - 2028
    Co-director
    Danish Pioneer Centre for AI Programme on Learning and Optimal Control in Dynamical Systems
  • 2026 - 2026
    Co-organizer
    ICLR Workshop: Multi-Agent Learning and Its Opportunities in the Era of Generative AI
  • 2025 - 2025
    Teaching Staff and Co-organizer
    Spring School on Reinforcement Learning and Control, CWI
    Ran tutorials on reinforcement learning for an interdisciplinary group of students, plus organizational duties.
  • 2024 - 2025
    Co-organizer
    AAAI Bridge Workshop: Collaborative AI and Modelling of Humans
    Co-organized both editions of this workshop at the AAAI Conference on Artificial Intelligence; the 2024 edition reached 300 registrations.
  • 2023 - 2025

    The Netherlands

    Postdoctoral Researcher
    Delft University of Technology
    Project on investigating advanced multi-agent reinforcement learning techniques for collaborative AI systems, funded for 3 years as part of the Dutch Hybrid Intelligence Centre.
  • 2023 - 2025
    Co-leader
    Hybrid Intelligence Centre Reinforcement Learning SIG
  • 2024 - 2024
    Invited Tutorial Speaker
    ELLIS Summer School on Collaborative and Generative AI
  • 2023 - 2023
    Invited Lecturer
    SIKS Course on RL for Adaptive Hybrid Intelligence
    Invited lecture on reinforcement learning for ad-hoc cooperation, part of a PhD course in the Netherlands Research School for Information and Knowledge Systems.
  • 2023 - 2023

    The Netherlands

    PhD Research Intern
    Dutch National Research Institute for Mathematics and Computer Science (CWI)
    Highly selective doctoral internship programme with stipend. Worked with Professor Wouter Koolen on the sample-complexity of Monte Carlo Tree Search.
  • 2018 - 2018
    Co-organizer and Instructor
    CS-E4070 - Probabilistic Modelling for Cognition and Interaction, Aalto University
    Designed and implemented a Master’s and PhD level special topic course together with Dr. Tomi Peltola.

Summary

Education

  • 2019 - 2023

    Finland

    PhD
    Aalto University
    Computer Science
    • Thesis: Model-based Multi-agent Reinforcement Learning for AI Assistants
    • Advisor: Professor Samuel Kaski
    • Opponent: Professor Matthew A. Taylor (University of Alberta)
    • Nominated for the Dean’s Award
  • 2016 - 2018

    Finland

    MSc
    Aalto University
    Machine Learning, Data Science and Artificial Intelligence (MACADAMIA)
    • Completed with honours (highest distinction)
  • 2011 - 2015

    Turkey

    BEng
    Selçuk University
    Computer Engineering
    • First-class honours (highest distinction)

Supervision

  • 2024 — Mia Choi, MSc in Cognitive Robotics, TU Delft: “Multi-Agent Reinforcement Learning for Portfolio Management”, in collaboration with Robeco Investment.
  • 2024 — Aranya Sinha, MSc in Computer Science, TU Delft: “Risk-sensitive Reinforcement Learning for Portfolio Allocation”, in collaboration with Robeco Investment.
  • 2021 — Alex Hämäläinen, MSc in Computer Science, Aalto University: “Differentiable User Models”
  • 2019 — Ari-Pekka Härkönen, BSc in Computer Science, Aalto University: “Computational Models of Theory of Mind”

Awards and Grants

  • 2019 — ELLIS PhD Student. Nominated and accepted to the pan-European PhD programme of the European Lab for Learning and Intelligent Systems, as part of its first cohort.
  • 2019 — KAUTE Personal Research Grant. Personal doctoral grant from the Finnish Science Foundation for Technology and Economics, received four times in a row (2019-2023), totalling 96,000 euros.
  • 2020 — Aalto University Competitive Co-department Funding Recipient. PhD project granted co-department funding as part of an internal process.

Service

  • Program Committee Member: NeurIPS, ICML, ICLR, AAAI, AAMAS, STOC, BNAIC, JMLR, JAIR

Invited Workshops and Seminars

  • 2024 — Invited Attendee, Lorentz Centre Workshop: Research Environments for Human-Machine Teaming, Leiden, The Netherlands.
  • 2023 — Invited Attendee, Dagstuhl Workshop: Model Learning for Improved Trustworthiness in Autonomous Systems, Schloss Dagstuhl, Germany.

Publications

  • 2026
    Distributional Active Inference
    Forty-third International Conference on Machine Learning (ICML)
  • 2025
    On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents
    Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
  • 2025
    Value Improved Actor Critic Algorithms
    Advances in Neural Information Processing Systems (NeurIPS)
  • 2024
    Uncoupled Learning of Differential Stackelberg Equilibria with Commitments
    Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
  • 2022
    Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs
    Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS)