MENU

Lenart Treven

Lenart Treven
Lenart Treven
PhD Student
ETH Zurich
lenart.treven@inf.ethz.ch
Automation makes our lives easier, who wouldn't like to contribute to its development?

Lenart Treven is a PhD student at ETH Zurich. His area of research is Continuous time Reinforcement Learning. Lenart studied Mathematics at the University of Ljubljana (Slovenia) for his Bachelor and did a Data Science Master at ETH Zurich. During his studies he was a software developer intern at XLAB, worked as a Data Scientist for ETH Juniors and was preparing high school students for various Mathematics competitions.

Scientific Publications

Published
Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models
Conference on Neural Information Processing Systems (NeurIPS 2021)
Pages 29780 - 29793
Lenart Treven, Philippe Wenk, Florian Dörfler, Andreas Krause
Doi.org Collection

Research projects as Researcher

Title
Principal Investigators

Continuous-time Deep Model-based Reinforcement Learning

Florian Dörfler, Andreas Krause

Summary

We investigate how classical methods from system identification, dynamical systems, and control can be combined with techniques from non- parametric machine learning to develop a rigorous framework for continuous-time model-based deep reinforcement learning. Concretely, we will learn a continuous-time dynamics model via neural ordinary differential equations, along with associated uncertainty bounds that can be used to trade exploration and exploitation. Ultimately, our framework should enable control design for complex and uncertain systems, and we plan to apply it to problems in building automation and grid-connected converters.

People involved

Florian Dörfler
Andreas Krause
Lenart Treven
Florian Dörfler, Andreas Krause, Lenart Treven
Continuous-time Deep Model-based Reinforcement Learning
Florian Dörfler, Andreas Krause

We investigate how classical methods from system identification, dynamical systems, and control can be combined with techniques from non- parametric machine learning to develop a rigorous framework for continuous-time model-based deep reinforcement learning. Concretely, we will learn a continuous-time dynamics model via neural ordinary differential equations, along with associated uncertainty bounds that can be used to trade exploration and exploitation. Ultimately, our framework should enable control design for complex and uncertain systems, and we plan to apply it to problems in building automation and grid-connected converters.

Florian Dörfler
Andreas Krause
Lenart Treven
Florian Dörfler, Andreas Krause, Lenart Treven
99
2d302258-eb79-48e4-a277-d88660d68bfa