Deep reinforcement learning for efficient measurement of quantum devices

Deep reinforcement learning is an emerging machine approach which can teach a computer to learn from their actions and rewards similar the way humans experience. It offers many advantages in automating decision processes navigate large parameter spaces. This paper proposes novel efficient measurement of quantum devices based on deep learning. We focus double dot devices, demonstrating fully automatic identification specific transport features called bias triangles. Measurements targeting these are difficult automate, since triangles found otherwise featureless regions space. Our algorithm identifies mean time less than 30 minutes, sometimes as little 1 minute. approach, dueling Q-networks, be adapted broad range target features. crucial demonstration utility for making operation devices.