10-15 ottobre 2021
Europe/Rome timezone

Quantum speed-ups in reinforcement learning

11 ott 2021, 12:00
25m
Oral Session 1

Speaker

Dr. Valeria Saggio (University of Vienna)

Description

Within artificial intelligence, of particular interest is reinforcement learning (RL), where autonomous agents learn to accomplish tasks via feedback exchange with their environment (the world they interact with). Thanks to rapid advances in quantum technologies, the idea of using quantum physics to boost the performance of RL agents was developed. I will focus on the bridge between RL and quantum mechanics, and show that a reduction in the agent’s learning time is possible if agents and environments also interact quantum-mechanically[1]. This idea was implemented on a fully-tunable photonic processor. The achieved speed-up in learning time, compared to the fully classical picture, confirms the potential of quantum technologies for future RL applications.

[1] Saggio, V. et al. Nature 591, 229–233 (2021).

Primary author

Dr. Valeria Saggio (University of Vienna)

Presentation Materials

There are no materials yet.
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now

×