Deep Q-learning decoder for depolarizing noise on the toric code

Abstract

We present an AI-based decoding agent for quantum error correction of depolarizing noise on the toric code. The agent is trained using deep reinforcement learning (DRL), where an artificial neural network encodes the state-action Q-values of error-correcting $X$, $Y$, and $Z$ Pauli operations, occurring with probabilities $p_x$, $p_y$, and $p_z$, respectively. By learning to take advantage of the correlations between bit-flip and phase-flip errors, the decoder outperforms the minimum-weight-perfect-matching (MWPM) algorithm, achieving higher success rate and higher error threshold for depolarizing noise ($p_z=p_x=p_y$), for code distances $d\le 9$. The decoder trained on depolarizing noise also has close to optimal performance for uncorrelated noise and provides functional but sub-optimal decoding for biased noise ($p_z\ne p_x=p_y$). We argue that the DRL-type decoder provides a promising framework for future practical error correction of topological codes, striking a balance between on-the-fly calculations, in the form of forward evaluation of a deep Q-network, and pre-training and information storage. The complete code, as well as ready-to-use decoders (pre-trained networks), can be found in the repository https://github.com/mats-granath/toric-RL-decoder.

arXiv comment8+10 pages, 10+8 figures

References in corpus (44)

• Fault-tolerant quantum computation by anyons
• Surface codes: Towards practical large-scale quantum computation
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Topological quantum memory
• Machine learning phases of matter
• Quantum Error Correction for Quantum Memories
• Microwave photonics with superconducting quantum circuits
• State preservation by repetitive error detection in a superconducting quantum circuit
• Learning phase transitions by confusion
• Realization of Three-Qubit Quantum Error Correction with Superconducting Circuits
• The Flux Qubit Revisited to Enhance Coherence and Reproducibility
• Detecting arbitrary quantum errors via stabilizer measurements on a sublattice of the surface code
• Experimental Quantum Computations on a Topologically Encoded Qubit
• Stabilizing entanglement autonomously between two superconducting qubits
• Fluctuations of Energy-Relaxation Times in Superconducting Qubits
• Decoherence benchmarking of superconducting qubits
• Reinforcement Learning in Different Phases of Quantum Control
• Detecting bit-flip errors in a logical qubit using stabilizer measurements
• Fast Decoders for Topological Quantum Codes
• Experimental demonstration of fault-tolerant state preparation with superconducting qubits
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Efficient Algorithms for Maximum Likelihood Decoding in the Surface Code
• Experimental demonstration of topological error correction
• A Neural Decoder for Topological Codes
• Fault-tolerant quantum error detection
• Optimizing Quantum Error Correction Codes with Reinforcement Learning
• Strong Resilience of Topological Codes to Depolarization
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Experimental demonstration of a graph state quantum error-correction code
• Measurement-based quantum computation with trapped ions
• Decoding Small Surface Codes with Feedforward Neural Networks
• Deep Neural Network Probabilistic Decoder for Stabilizer Codes
• High threshold error correction for the surface code
• Surface code with decoherence: An analysis of three superconducting architectures
• Quantum error correction for the toric code using deep reinforcement learning
• Global optimization of quantum dynamics with AlphaZero deep exploration
• Deep neural decoders for near term fault-tolerant experiments
• An efficient Markov chain Monte Carlo algorithm for the surface code
• Advantages of versatile neural-network decoding for topological codes
• Cellular-automaton decoders with provable thresholds for topological codes
• Cellular-automaton decoders for topological quantum memories
• Hamiltonian Learning for Quantum Error Correction
• Scalable Neural Network Decoders for Higher Dimensional Quantum Codes
• Reinforcement learning for optimal error correction of toric codes

Cited by in corpus (19)

• Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Neural-network quantum state tomography
• Decoding algorithms for surface codes
• Scalable Neural Decoder for Topological Surface Codes
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Hessian-based optimization of constrained quantum control
• Techniques for combining fast local decoders with global decoders under circuit-level noise
• Simultaneous Discovery of Quantum Error Correction Codes and Encoders with a Noise-Aware Reinforcement Learning Agent
• Determination of the Semion Code Threshold using Neural Decoders
• Data-driven decoding of quantum error correcting codes using graph neural networks
• Taming quantum systems: A tutorial for using shortcuts-to-adiabaticity, quantum optimal control, and reinforcement learning
• Neural network decoder for near-term surface-code experiments
• Classification and reconstruction of optical quantum states with deep neural networks
• Error-rate-agnostic decoding of topological stabilizer codes
• A NEAT Quantum Error Decoder
• Enhancing Quantum Memory Lifetime with Measurement-Free Local Error Correction and Reinforcement Learning
• Superclassical non-Markovian open quantum dynamics
• Neural Decoders for Universal Quantum Algorithms