Deep Q-learning decoder for depolarizing noise on the toric code
David Fitzek, Mattias Eliasson, Anton Frisk Kockum, Mats Granath · Physical Review Research · 2020
This paper presents an artificial intelligence-based decoder for quantum error correction of the toric code. A neural network is trained, using reinforcement learning, to suggest error-correcting operations on the physical qubits to best avoid logical errors. By learning to take advantage of the correlations between bit-flip and phase-flip errors, it can outperform the standard matching decoder for depolarizing noise.