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

Dec 08, 2025	I will be Editor for the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Oct 27, 2025	As part of our Robotics lecture in Period 1 students and my group visited the Amsterdam startup Monumental to see and learn about the use of AI and Robotics in Construction. See here the VU news article!
Oct 16, 2025	As part of our outreach we welcome today the CS faculty and students to our Robotics Lab Day! Come and visit us and see our robots in actions, with students presenting their latest research and thesis work!
Oct 15, 2025	Next week I will present our work on co-design of robots with self-imitation learning and reinforcement learning at the IEEE/RSJ International Conference on Intelligent Robots and Systems 2025 in Hangzhou, China: “Co-Adaptation of Embodiment and Control with Self-Imitation Learning”.
Oct 15, 2025	We had two papers accepted and presented at the Artificial Life conference on topics in co-design of robots! One paper on “Understanding the Navigation of Robot Morphology Spaces with Local Optima Network Analysis” with the awesome Sarah Thompson on new approaches and analysis of the design space of robot morphologies. The second paper with my collaborateur Kishan Nagiredla on “COGENT: Co-design of Robots with Generative Flow Networks” using Generative Flow networks to co-optimize the embodiment and behaviour of robotic agents.
Sep 15, 2025	Welcome to Michael Przystupa who is joining my lab as postdoc on the ETAPE project.
Sep 10, 2025	At next weeks Europen Workshop on Reinforcement Leanring (EWRL 2025) my group will present three papers: “COGENT: Co-design of Robots with GFlowNets” with Kishan Reddy Nagiredla, Arun Kumar AV, Kevin Sebastian Luck, Thommen George Karimpanal, Santu Rana “TE-RoboNet: Transfer Enhanced RoboNet for Sample-Efficient Generation of Robot Co-Designs” with Kishan Reddy Nagiredla, Arun Kumar AV, Kevin Sebastian Luck, Thommen George Karimpanal, Santu Rana “Co-Design and Control of a Biomimetic Snake Robot and its Contact Surfaces with Reinforcement Learning” with Liza Darwesh, Riccardo Pretto, Sylvia Cressman, Tiia Tikkala, Shivam Chaubey, Kevin Sebastian Luck
Jul 13, 2025	I will be co-organizer, program chair and workflow chair for the 18th European Workshop on Reinforcement Leanring (EWRL 2025) in Tuebingen, Germany!
Jun 20, 2025	Our paper on “Co-Adaptation of Embodiment and Control with Self-Imitation Learning” got accepted to IROS 205! Congrats to Sergio for the great work on this paper!
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).

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},
}

CoRL

Learning Transparent Reward Models via Unsupervised Feature Selection

Daulet Baimukashev , Gokhan Alcan , Kevin Sebastian Luck , and Ville Kyrki

In 8th Annual Conference on Robot Learning , 30 oct–01 nov 2024

Bib PDF

@inproceedings{baimukashevlearning,
  title = {Learning Transparent Reward Models via Unsupervised Feature Selection},
  author = {Baimukashev, Daulet and Alcan, Gokhan and Luck, Kevin Sebastian and Kyrki, Ville},
  booktitle = {8th Annual Conference on Robot Learning},
  year = {2024}
}

Discrete Codebook World Models for Continuous Control

Aidan Scannell , Mohammadreza Nakhaeinezhadfard , Kalle Kujanpää , Yi Zhao , Kevin Sebastian Luck , Arno Solin , and Joni Pajarinen

In The Thirteenth International Conference on Learning Representations , 30 oct–01 nov 2025

Bib PDF

@inproceedings{scannelldiscrete,
  title = {Discrete Codebook World Models for Continuous Control},
  author = {Scannell, Aidan and Nakhaeinezhadfard, Mohammadreza and Kujanp{\"a}{\"a}, Kalle and Zhao, Yi and Luck, Kevin Sebastian and Solin, Arno and Pajarinen, Joni},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
}

Co-Adaptation of Embodiment and Control with Self-Imitation Learning

Sergio Hernández-Gutiérrez , Ville Kyrki , and Kevin Sebastian Luck

In 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 30 oct–01 nov 2025

Bib PDF

@inproceedings{hernandez2025co,
  title = {Co-Adaptation of Embodiment and Control with Self-Imitation Learning},
  author = {Hern{\'a}ndez-Guti{\'e}rrez, Sergio and Kyrki, Ville and Luck, Kevin Sebastian},
  booktitle = {2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages = {4393--4400},
  year = {2025},
  organization = {IEEE},
}