Kevin Sebastian Luck

Assistant Professor

I am an Assistant Professor in the Computational Intelligence Group at the Vrije Universiteit Amsterdam. Here, I am working on multiple different topics in the field of robot learning, primarily in the area of deep reinforcement learning.

One area of particular interest of mine is the combination of deep reinforcement learning with evolutionary principles, for the development of AI-assisted design methodologies and physical/embodied intelligence, to allow robots to co-adapt both their behaviour and morpoholgy.

Before I joined Amsterdam I worked as postdoctoral researcher at the Aalto University and the Finnish Center for Artificial Intelligence in Espoo (Helsinki), Finland, where I am/was hosted by the Intelligent Robotics Group of Ville Kyrki.

Keywords: (Deep) Reinforcement Learning, Robot Learning, Embodied Intelligence, Evolving Robots

news

Mar 15, 2025	I successfully passed my tenure review at the Vrije Universiteit Amsterdam.
Feb 28, 2025	Congratulations to Aidan Scannell and Mohammadreza Nakhaei for their accepted paper at ICLR 2025 on Discrete Codebook World Models for Continuous Control. This paper was a collaboration with the Finnish Center for AI and Aalto University, supported by the Dutch Research Council, and while Mohammadreza was a visiting PhD student at our lab.
Jan 13, 2025	New year, new goals and new grants for our lab: The Dutch Research Council NWO and the AIned Foundation will support my lab with a NWO AIned XS “High Gain-High Risk” grant for the project ETAPE: Embodiment- and Task-Aware Parameter Embeddings for Robotic Foundation Models.
Jan 08, 2025	I will be Editor for the IEEE International Conference on Intelligent Robotics and Systems (IROS) 2025.
Nov 09, 2024	We organized a workshop on Morphology-Aware Policy and Design Learning at the Conference on Robot Learning. If you are interested in cross-embodiment learning, embodiment-aware learning or Co-Design of robot behaviour and design, then check out our live stream. Also congratulations to all accepted workshop authors!
Nov 07, 2024	Daulet Baimukashev presented our work on “Learning Interpretable Reward Models via Unsupervised Feature Selection” at the Conference on Robot Learning 2024 in Munich, Germany. This was a joint collaboration with Gökhan Alcan (Tampere University) and Ville Kyrki (Aalto University).
Oct 30, 2024	I presented our work on self-imitation learning for co-design at the European Workshop on Reinforcement Learning 2024 in Toulouse, France: Following Ancestral Footsteps: Co-Designing Morphology and Behaviour with Self-Imitation Learning. This work was together with my Master student Sergio Hernández-Gutiérrez and Prof. Ville Kyrki from Aalto University.
Oct 15, 2024	Xinrui Zu is joining my group as a PhD student, who is jointly supervised with Assistant Professor Shujian Yu.
Oct 01, 2024	Happy to welcome Dr. Ariyan Bighashdel to my group, joining as postdoc. He will be working on our NWO-funded TeNet project.
Sep 23, 2024	We presented our abstract about applying co-design to snake robots at the 40th ICRA anniversity conference (ICRA@40) in Rotterdam, Netherlands. This was work done by my two amazing Master students Riccardo Pretto and Sylvia Cressman, in collaboration with Michael Andrew Jansen from the Smithsonian Institute in Washington DC, and my two finnish collegues Shivam Chaubey and Ville Kyrki.
Sep 16, 2024	Happy to welcome Mohammadreza Nakhaei as a visiting PhD student to my group for the next 5 months.
Sep 01, 2024	Bringing more Robotics to the VU Amsterdam! Starting now in the new academic year we will have for the first time a foundational Robotics course in the CS/AI curriculum for Bachelor students. Lot’s of work, but we have assembled a great team with Kim Baraka as co-teacher and Mark Adamik as the lead for the practicals.
Aug 30, 2024	I presented our work on Accelerating Laboratory Automation Through Robot Skill Learning For Sample Scraping at IEEE CASE 2024 in Bari, Italy. This was a collaboration with an amazing team at the University of Liverpool, shout-out to my awesome collegue Gabriella Pizzuto for putting this work together! The paper was also nominated for the Best Healthcare Application award at CASE 2024!
Jul 25, 2024	I gave an invited talk about our research on Co-Design with Robot Learning at the MILA Robot Learning Seminar.
Jul 15, 2024	Congratulations to Sergio Hernandez! Our paper Following Ancestral Footsteps: Co-Designing Agent Morphology and Behaviour with Self-Imitation Learning won the best paper award at the R:SS Workshop on Embodiment-Aware Robot Learning (EARL).

selected publications

AAAI

Sparse latent space policy search

Kevin Sebastian Luck , Joni Pajarinen , Erik Berger , Ville Kyrki , and Heni Ben Amor

In Proceedings of the AAAI Conference on Artificial Intelligence , 2016

Bib PDF

@inproceedings{luck2016sparse,
  title = {Sparse latent space policy search},
  author = {Luck, Kevin Sebastian and Pajarinen, Joni and Berger, Erik and Kyrki, Ville and Amor, Heni Ben},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {30},
  number = {1},
  year = {2016},
}

R:SS

From the Lab to the Desert: Fast Prototyping and Learning of Robot Locomotion

Kevin Sebastian Luck , Joseph Campbell , Michael Jansen , Daniel Aukes , and Heni Ben Amor

In Proceedings of Robotics: Science and Systems , Jul 2017

Bib PDF

@inproceedings{Luck-RSS-17,
  author = {Luck, Kevin Sebastian and Campbell, Joseph and Jansen, Michael and Aukes, Daniel and Amor, Heni Ben},
  title = {From the Lab to the Desert: Fast Prototyping and Learning of Robot Locomotion},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2017},
  address = {Cambridge, Massachusetts},
  month = jul,
  doi = {10.15607/RSS.2017.XIII.075},
}

CoRL
Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning

Kevin Sebastian Luck , Heni Ben Amor , and Roberto Calandra

In Proceedings of the Conference on Robot Learning , 30 oct–01 nov 2020

Abs Bib PDF

Humans and animals are capable of quickly learning new behaviours to solve new tasks. Yet, we often forget that they also rely on a highly specialized morphology that co-adapted with motor control throughout thousands of years. Although compelling, the idea of co-adapting morphology and behaviours in robots is often unfeasible because of the long manufacturing times, and the need to redesign an appropriate controller for each morphology. In this paper, we propose a novel approach to automatically and efficiently co-adapt a robot morphology and its controller. Our approach is based on recent advances in deep reinforcement learning, and specifically the soft actor critic algorithm. Key to our approach is the possibility of leveraging previously tested morphologies and behaviors to estimate the performance of new candidate morphologies. As such, we can make full use of the information available for making more informed decisions, with the ultimate goal of achieving a more data-efficient co-adaptation (i.e., reducing the number of morphologies and behaviors tested). Simulated experiments show that our approach requires drastically less design prototypes to find good morphology-behaviour combinations, making this method particularly suitable for future co-adaptation of robot designs in the real world.
@inproceedings{pmlr-v100-luck20a, title = {Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning}, author = {Luck, Kevin Sebastian and Amor, Heni Ben and Calandra, Roberto}, booktitle = {Proceedings of the Conference on Robot Learning}, pages = {854--869}, year = {2020}, editor = {Kaelbling, Leslie Pack and Kragic, Danica and Sugiura, Komei}, volume = {100}, series = {Proceedings of Machine Learning Research}, month = {30 Oct--01 Nov}, publisher = {PMLR}, url = {https://proceedings.mlr.press/v100/luck20a.html}, }

NeurIPS

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

Mhairi Dunion , Trevor McInroe , Kevin Sebastian Luck , Josiah P. Hanna , and Stefano V Albrecht

In Thirty-seventh Conference on Neural Information Processing Systems , 30 oct–01 nov 2023

Bib PDF

@inproceedings{dunion2023conditional,
  title = {Conditional Mutual Information for Disentangled Representations in Reinforcement Learning},
  author = {Dunion, Mhairi and McInroe, Trevor and Luck, Kevin Sebastian and Hanna, Josiah P. and Albrecht, Stefano V},
  booktitle = {Thirty-seventh Conference on Neural Information Processing Systems},
  year = {2023},
  url = {https://openreview.net/forum?id=EmYWJsyad4},
}

AAAI

Co-imitation: learning design and behaviour by imitation

Chang Rajani , Karol Arndt , David Blanco-Mulero , Kevin Sebastian Luck , and Ville Kyrki

In Proceedings of the AAAI Conference on Artificial Intelligence , 30 oct–01 nov 2023

Bib PDF

@inproceedings{rajani2023co,
  title = {Co-imitation: learning design and behaviour by imitation},
  author = {Rajani, Chang and Arndt, Karol and Blanco-Mulero, David and Luck, Kevin Sebastian and Kyrki, Ville},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {37},
  number = {5},
  pages = {6200--6208},
  year = {2023},
}