Publications

2025

1. NeurIPS

   

   Optimism via intrinsic rewards: Scalable and principled exploration for model-based reinforcement learning

   Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza, and 3 more authors

   In 7th Robot Learning Workshop: Towards Robots with Human-Level Abilities, 2025

   Bib

   @inproceedings{sukhija2025optimism,
     title = {Optimism via intrinsic rewards: Scalable and principled exploration for model-based reinforcement learning},
     author = {Sukhija, Bhavya and Treven, Lenart and Sferrazza, Carmelo and Dorfler, Florian and Abbeel, Pieter and Krause, Andreas},
     booktitle = {7th Robot Learning Workshop: Towards Robots with Human-Level Abilities},
     year = {2025},
   }

2. ICLR

   

   ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

   Yarden As, Bhavya Sukhija, Lenart Treven, and 3 more authors

   In The Thirteenth International Conference on Learning Representations, 2025

   Bib

   @inproceedings{as2025actsafe,
     title = {ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning},
     author = {As, Yarden and Sukhija, Bhavya and Treven, Lenart and Sferrazza, Carmelo and Coros, Stelian and Krause, Andreas},
     booktitle = {The Thirteenth International Conference on Learning Representations},
     year = {2025},
     url = {https://openreview.net/forum?id=aKRADWBJ1I},
   }

2024

1. NeurIPS

   

   When to sense and control? a time-adaptive approach for continuous-time RL

   Lenart Treven, Yarden As, Florian Dorfler, and 1 more author

   Advances in Neural Information Processing Systems, 2024

   Bib

   @article{treven2024sense,
     title = {When to sense and control? a time-adaptive approach for continuous-time RL},
     author = {Treven, Lenart and As, Yarden and Dorfler, Florian and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems},
     volume = {37},
     pages = {63654--63685},
     year = {2024},
   }

2. NeurIPS

   

   Neorl: Efficient exploration for nonepisodic rl

   Lenart Treven, Florian Dorfler, Stelian Coros, and 1 more author

   Advances in Neural Information Processing Systems, 2024

   Bib

   @article{treven2024neorl,
     title = {Neorl: Efficient exploration for nonepisodic rl},
     author = {Treven, Lenart and Dorfler, Florian and Coros, Stelian and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems},
     volume = {37},
     pages = {74966--74998},
     year = {2024},
   }

3. NeurIPS

   

   Transductive active learning: Theory and applications

   Jonas Hübotter, Lenart Treven, Yarden As, and 1 more author

   Advances in Neural Information Processing Systems, 2024

   Bib

   @article{hubotter2024transductive,
     title = {Transductive active learning: Theory and applications},
     author = {H{\"u}botter, Jonas and Treven, Lenart and As, Yarden and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems},
     volume = {37},
     pages = {124686--124755},
     year = {2024},
   }

4. IROS

   

   Bridging the sim-to-real gap with Bayesian inference

   Jonas Rothfuss, Bhavya Sukhija, Lenart Treven, and 3 more authors

   In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

   Bib

   @inproceedings{rothfuss2024bridging,
     title = {Bridging the sim-to-real gap with Bayesian inference},
     author = {Rothfuss, Jonas and Sukhija, Bhavya and Treven, Lenart and D{\"o}rfler, Florian and Coros, Stelian and Krause, Andreas},
     booktitle = {2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
     pages = {10784--10791},
     year = {2024},
     organization = {IEEE},
   }

5. ICLR Workshop

   

   Active Few-Shot Fine-Tuning

   Jonas Hübotter, Bhavya Sukhija, Lenart Treven, and 2 more authors

   CoRR, 2024

   Bib

   @article{DBLP:journals/corr/abs-2402-15441,
     publtype = {informal},
     author = {Hübotter, Jonas and Sukhija, Bhavya and Treven, Lenart and As, Yarden and Krause, Andreas},
     title = {Active Few-Shot Fine-Tuning},
     year = {2024},
     cdate = {1704067200000},
     journal = {CoRR},
     volume = {abs/2402.15441},
     url = {https://doi.org/10.48550/arXiv.2402.15441},
   }

2023

1. NeurIPS

   

   Efficient exploration in continuous-time model-based reinforcement learning

   Lenart Treven, Jonas Hübotter, Bhavya Sukhija, and 2 more authors

   Advances in Neural Information Processing Systems, 2023

   Bib

   @article{treven2023efficient,
     title = {Efficient exploration in continuous-time model-based reinforcement learning},
     author = {Treven, Lenart and H{\"u}botter, Jonas and Sukhija, Bhavya and Dorfler, Florian and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems},
     volume = {36},
     pages = {42119--42147},
     year = {2023},
   }

2. NeurIPS

   

   Optimistic active exploration of dynamical systems

   Bhavya Sukhija, Lenart Treven, Cansu Sancaktar, and 3 more authors

   Advances in Neural Information Processing Systems, 2023

   Bib

   @article{sukhija2023optimistic,
     title = {Optimistic active exploration of dynamical systems},
     author = {Sukhija, Bhavya and Treven, Lenart and Sancaktar, Cansu and Blaes, Sebastian and Coros, Stelian and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems},
     volume = {36},
     pages = {38122--38153},
     year = {2023},
   }

2021

1. NeurIPS

   

   Distributional gradient matching for learning uncertain neural dynamics models

   Lenart Treven, Philippe Wenk, Florian Dorfler, and 1 more author

   Advances in Neural Information Processing Systems, 2021

   Bib

   @article{treven2021distributional,
     title = {Distributional gradient matching for learning uncertain neural dynamics models},
     author = {Treven, Lenart and Wenk, Philippe and Dorfler, Florian and Krause, Andreas},
     journal = {Advances in Neural Information Processing Systems},
     volume = {34},
     pages = {29780--29793},
     year = {2021},
   }

2. L4DC

   

   Learning stabilizing controllers for unstable linear quadratic regulators from a single trajectory

   Lenart Treven, Sebastian Curi, Mojmı́r Mutnỳ, and 1 more author

   In Learning for dynamics and control, 2021

   Bib

   @inproceedings{treven2021learning,
     title = {Learning stabilizing controllers for unstable linear quadratic regulators from a single trajectory},
     author = {Treven, Lenart and Curi, Sebastian and Mutn{\`y}, Mojm{\'\i}r and Krause, Andreas},
     booktitle = {Learning for dynamics and control},
     pages = {664--676},
     year = {2021},
     organization = {PMLR},
   }