Research Interests
Reinforcement Learning, Optimization, Information Theory
Short CV
- 2021 - to present: Postdoc, University of Tübingen (prior in MPI-IS Tübingen)
- 2019: Postdoc, MPI-INF Saarbrücken
- 2018: Doctor in Computer Science, Saarland University, Affiliated with MPI-INF and Cluster of Excellence MMCI
Selected Publications
- Cheng J, Vlastelica M, Kolev P, et al. Learning diverse skills for local navigation under multi-constraint optimality[J]. arXiv preprint arXiv:2310.02440, 2023. project page
- Vlastelica M, Kolev P, Cheng J, et al. Diverse offline imitation via fenchel duality[J]. arXiv preprint arXiv:2307.11373, 2023. project page
- Ramponi G, Kolev P, Pietquin O, et al. On imitation in mean-field games[J]. Advances in Neural Information Processing Systems, 2024, 36.
- Kolev P, Martius G, Muehlebach M. Online learning under adversarial nonlinear constraints[J]. Advances in Neural Information Processing Systems, 2024, 36.
- Li C, Blaes S, Kolev P, et al. Versatile skill control via self-supervised adversarial imitation of unlabeled mixed motions[C]//2023 IEEE international conference on robotics and automation (ICRA). IEEE, 2023: 2944-2950. project page
- Gürtler N, Blaes S, Kolev P, et al. Benchmarking offline reinforcement learning on real-robot hardware[J]. arXiv preprint arXiv:2307.15690, 2023. project page
Teaching
Lecture
- Reinforcement Learning, Summer 2023, Winter 2024
- Optimization, Summer 2019, 2017, 2013
- Machine Learning, Winter 2012