Pascal Klink

Research Interests

  • Reinforcement Learning
  • Transfer- and Curriculum Learning
  • Bayesian Inference
  • Robotics and Optimal Control.

Affiliation

TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department

Contact Information

pascal.klink@robot-learning.de
Room E327, Building S2|02, TU Darmstadt, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-25371





Pascal joined the Intelligent Autonomous Systems Group in May 2019 as a PhD student working on the ROBOLEAP project. He defended his PhD thesis in November 2023. In general, his research interests revolve around various aspects of reinforcement learning that, in his opinion, will be crucial to tackling challenging reinforcement learning problems - two of them being knowledge transfer and learning via curricula. He is convinced that learning systems need to be able to reuse previously acquired knowledge to speed up and bootstrap learning in new situations in order to tackle the most challenging tasks.

Before starting his PhD, Pascal completed his Bachelor's degree in Computer Science and Master's degree in Autonomous Systems at the Technische Universitaet Darmstadt. He wrote his Master's thesis on "Generalization and Transferability in Reinforcement Learning" supervised by Hany Abdulsamad, Boris Belousov and Jan Peters, where he investigated concepts from the domain of numerical continuation, parameteric programming and concurrent systems theory for the task of knowledge transfer and finally developed a method for autonomous curriculum generation for reinforcement learning problems.

Key References

Curriculum- and Transfer Learning

    •       Bib
      Klink, P.; Wolf, F.; Ploeger, K.; Peter, J.; Pajarinen, J. (submitted). Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning, Submitted to the IEEE Transactions on Robotics (T-Ro).
    •     Bib
      Klink, P.; D'Eramo, C.; Peters, J.; Pajarinen, J. (in press). On the Benefit of Optimal Transport for Curriculum Reinforcement Learning, IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI).
    •     Bib
      Klink, P.; Yang, H.; D'Eramo, C.; Peters, J.; Pajarinen, J. (2022). Curriculum Reinforcement Learning via Constrained Optimal Transport, International Conference on Machine Learning (ICML).
    •     Bib
      Klink, P.; D`Eramo, C.; Peters, J.; Pajarinen, J. (2022). Boosted Curriculum Reinforcement Learning, International Conference on Learning Representations (ICLR).
    •     Bib
      Klink, P.; Abdulsamad, H.; Belousov, B.; D'Eramo, C.; Peters, J.; Pajarinen, J. (2021). A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning, Journal of Machine Learning Research (JMLR).
    •     Bib
      Klink, P.; D'Eramo, C.; Peters, J.; Pajarinen, J. (2020). Self-Paced Deep Reinforcement Learning, Advances in Neural Information Processing Systems (NIPS / NeurIPS).
    •     Bib
      Klink, P.; Abdulsamad, H.; Belousov, B.; Peters, J. (2019). Self-Paced Contextual Reinforcement Learning, Proceedings of the 3rd Conference on Robot Learning (CoRL).
    •   Bib
      Klink, P.; Peters, J. (2019). Measuring Similarities between Markov Decision Processes, 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM).

Approximate Bayesian Inference for Machine Learning

    •     Bib
      Abdulsamad, H.; Nickl, P.; Klink, P.; Peters, J. (2024). Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 46, 4, pp.1950-1963.
    •     Bib
      Abdulsamad, H.; Nickl, P.; Klink, P.; Peters, J. (2021). A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning, Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).
    •     Bib
      Watson, J.; Lin, J. A.; Klink, P.; Peters, J. (2021). Neural Linear Models with Functional Gaussian Process Priors, 3rd Symposium on Advances in Approximate Bayesian Inference (AABI).
    •     Bib
      Watson, J.; Lin J. A.; Klink, P.; Pajarinen, J.; Peters, J. (2021). Latent Derivative Bayesian Last Layer Networks, Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS).

Tree Search

    •       Bib
      Dam, T.; Klink, P.; D'Eramo, C.; Peters, J.; Pajarinen, J. (2020). Generalized Mean Estimation in Monte-Carlo Tree Search, Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

Books

    •     Bib
      Belousov, B.; Abdulsamad H.; Klink, P.; Parisi, S.; Peters, J. (2021). Reinforcement Learning Algorithms: Analysis and Applications, Studies in Computational Intelligence, Springer International Publishing.