Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation*

Topological error correcting codes, and particularly the surface code, provide a promising and feasible roadmap towards large-scale fault-tolerant quantum computation. Obtaining fast and flexible decoding algorithms for these codes, within the experimentally relevant context of faulty syndrome measurements, is therefore an important milestone. The problem of decoding such codes, in the full fault-tolerant setting, can be naturally reformulated as a process of repeated interactions between a decoding agent and a code environment. Reinforcement learning can then be used to obtain such a decoding agent, and can succesfully learn to decode in the fault-tolerant setting.