NTR Webinar: Interferobot, Aligning an Optical Interferometer by a Reinforcement Learning Agent

NTR organizes and hosts scientific webinars on neural networks and invites speakers from all over the world to present their recent work at the webinars.

On March 16 Dmitry Sorokin, Russian Quantum Center, Moscow, Russia, led a technical Zoom webinar on Interferobot, Aligning an Optical Interferometer by a Reinforcement Learning Agent.

About the webinar: 

Today‚Äôs robots can be used in a limited number of settings due to the limitations of classical approaches to robot control. 

The use of machine learning, especially reinforcement learning, will allow robots to solve difficult-to-formalize problems in the real world. 

Example: The application of reinforcement learning to implement a robot that aligns an optical Interferometer. 

The robot receives interference patterns from a camera and, experimenting with the available actions, learns to align the setup without any human supervision. A robot trained in simulation is then able to align a real setup at the level of a human expert.

Materials available:

Webinar presentation.

Moderator and contact:
NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.

Leave a Reply

Your email address will not be published. Required fields are marked *