Speaker
Description
Reinforcement Learning (RL) is one of the central and most interesting topics in the current ML landscape. In particular, at the light source BESSY II, the development of Deep RL agents for performance improvement is a field of interest since 2019 and is been already carried out in several use cases at the machine (booster current optimisation, injection efficiency, mitigation of harmonic orbit perturbations...) with promising results. Besides, interpretability methods applied to the trained agents are giving interesting insights about the learning process and the machine itself. In the context of an eventual ErUM proposal we would like to share experiences with further use cases in other facilities, improve the natural challenges associated with RL-loops (learning stability, hardware issues...) and expand our RL/ML-toolset with additional methods.
My current most burning research question, I like to find partners for, is:
Reinforcement Learning for the Automation and Improvement of Large-Scale Facilities Operation
Please describe areas in which you can contribute to “data handling” teaching.
Real-time loops, optimisation.
In ErUM-Data, what kind of data are you dealing with?
Mostly moderate-to-high-dimensional data obtained from real-time interaction with the accelerator.
What is your expertise in computing and / or software development?
Mathematician, seven years of experience in the development and application of ML algorithms in industry and research.
What is your field and role?
Data Scientist at the Operation Accelerator Department, BESSY II - Helmholtz Zentrum Berlin
Please describe your expertise/areas in which you would like to contribute / advise.
Reinforcement Learning, general ML, model interpretability and visualisation.
Please describe areas in which you would like to improve your knowledge / skills.
Hardware, stability issues, extended physics applications.
| Your ErUM - Committee is | More than one |
|---|---|
| List of Committees: | KfB, KFS |
| Do you consent to the data usage and public abstract data posting in the ErUM-Data Community Information Exchange? | Yes |
