Aligning an optical interferometer with beam divergence control and continuous action space

Stepan Makarenko, Dmitry Igorevich Sorokin, Alexander Ulanov, Alexander Lvovsky
Proceedings of the 5th Conference on Robot Learning, PMLR 164:918-927, 2022.

Abstract

Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.

Cite this Paper

BibTeX
@InProceedings{pmlr-v164-makarenko22a, title = {Aligning an optical interferometer with beam divergence control and continuous action space}, author = {Makarenko, Stepan and Sorokin, Dmitry Igorevich and Ulanov, Alexander and Lvovsky, Alexander}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {918--927}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/makarenko22a/makarenko22a.pdf}, url = {https://proceedings.mlr.press/v164/makarenko22a.html}, abstract = {Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.} }
Endnote
%0 Conference Paper %T Aligning an optical interferometer with beam divergence control and continuous action space %A Stepan Makarenko %A Dmitry Igorevich Sorokin %A Alexander Ulanov %A Alexander Lvovsky %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-makarenko22a %I PMLR %P 918--927 %U https://proceedings.mlr.press/v164/makarenko22a.html %V 164 %X Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.
APA
Makarenko, S., Sorokin, D.I., Ulanov, A. & Lvovsky, A.. (2022). Aligning an optical interferometer with beam divergence control and continuous action space. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:918-927 Available from https://proceedings.mlr.press/v164/makarenko22a.html.

Related Material