Reinforcement learning pulses for transmon qubit entangling gates

TL;DR

This paper demonstrates how reinforcement learning can autonomously design high-fidelity, efficient entangling gates for superconducting transmon qubits without relying on detailed physical models, adapting to hardware variations.

Contribution

It introduces a model-free reinforcement learning approach for designing transmon qubit gates, outperforming standard methods in fidelity and duration, and adapts to hardware drift with minimal extra optimization.

Findings

Reinforcement learning successfully designs entangling gates with higher fidelity.

The method outperforms standard cross-resonance gates in speed and accuracy.

The approach adapts to hardware variations with little additional training.

Abstract

The utility of a quantum computer depends heavily on the ability to reliably perform accurate quantum logic operations. For finding optimal control solutions, it is of particular interest to explore model-free approaches, since their quality is not constrained by the limited accuracy of theoretical models for the quantum processor - in contrast to many established gate implementation strategies. In this work, we utilize a continuous-control reinforcement learning algorithm to design entangling two-qubit gates for superconducting qubits; specifically, our agent constructs cross-resonance and CNOT gates without any prior information about the physical system. Using a simulated environment of fixed-frequency, fixed-coupling transmon qubits, we demonstrate the capability to generate novel pulse sequences that outperform the standard cross-resonance gates in both fidelity and gate duration, while maintaining a comparable susceptibility to stochastic unitary noise. We further showcase an augmentation in training and input information that allows our agent to adapt its pulse design abilities to drifting hardware characteristics, importantly with little to no additional optimization. Our results exhibit clearly the advantages of unbiased adaptive-feedback learning-based optimization methods for transmon gate design.