aqora

Quantum circuit mapping based on discrete particle swarm optimization and deep reinforcement learning

Yang-Zhi Li, Wen Liu, Guosheng Xu +3 more

Swarm and Evolutionary ComputationApr 3, 20255 citations

Optimization of superconducting qubit capacitor geometry based on deep reinforcement learning

Chaojie Zhang, Weilong Wang, Jiaxin Li +5 more

Quantum Information ProcessingFeb 13, 20261 citation

Optimising Quantum Gate Fidelity with Deep Reinforcement Learning

Leander Grech, Gianluca Valentino, Simon Hirländer

Jan 1, 20240 citations

Optimizing Initial Qubit Mappings With Variable Connection Fidelity Using Deep Reinforcement Learning

Rares Adrian Oancea, Stan van der Linde, Willem de Kok +2 more

Quantum compilation requires solving the initial mapping problem, which is crucial for optimizing qubit assignment and minimizing fidelity in compiled quantum circuits. This study investigates the application of Deep Reinforcement Learning (DRL) to address initial mapping across various qubit topologies, while considering varying qubit connection fidelities. By leveraging policy gradient algorithms-Advantage Actor-Critic (A2C), Proximal Policy Optimization (PPO), Trust Region Policy Optimization (TRPO), and PPO with action masking-DRL agents effectively compute high-quality mappings for both small-and medium-scale quantum architectures, but their efficiency decreases as the system size grows, highlighting the need for further optimization strategies. Fine-tuning hyperparameters and incorporating action masking are shown to be essential for preventing illegal actions and enhancing mapping accuracy, particularly in larger systems. This research also aids the continued development of initial mapping techniques by introducing a comprehensive qubit connectivity database for systematic evaluation of DRL methods across diverse architectures.Quantum compilation requires solving the initial mapping problem, which is crucial for optimizing qubit assignment and minimizing fidelity in compiled quantum circuits. This study investigates the application of Deep Reinforcement Learning (DRL) to address initial mapping across various qubit topologies, while considering varying qubit connection fidelities. By leveraging policy gradient algorithms-Advantage Actor-Critic (A2C), Proximal Policy Optimization (PPO), Trust Region Policy Optimization (TRPO), and PPO with action masking-DRL agents effectively compute high-quality mappings for both small-and medium-scale quantum architectures, but their efficiency decreases as the system size grows, highlighting the need for further optimization strategies. Fine-tuning hyperparameters and incorporating action masking are shown to be essential for preventing illegal actions and enhancing mapping accuracy, particularly in larger systems. This research also aids the continued development of initial mapping techniques by introducing a comprehensive qubit connectivity database for systematic evaluation of DRL methods across diverse architectures.

Nov 20, 20240 citations

Quantum State Generation Via Deep Reinforcement Learning

Shaojun Wu, Shan Jin, Xiaoting Wang

The quantum state generation problem is a major research goal of quantum control and quantum variational algorithms, which use iterative optimization methods to evolve the initial state to the target state. The Twin Delayed Deep Deterministic Policy (TD3) algorithm in reinforcement learning achieves high learning efficiency and better stability in continuous control tasks. Here, using the TD3, we propose a new quantum state preparation method that does not require case-by-case optimization, to find a suitable evolution path to obtain the desired state. Specifically, we input the initial state into the trained actor-network, which can output the parameters of the unitary gates step by step, thus gradually evolving the initial state to the fixed quantum state. According to the reversibility of the unitary transformation, we can obtain a sequence of unitary gates to evolve the fixed state to the desired state. To verify the effectiveness of the algorithm, we perform simulations for one-qubit, two-qubit, and four-qubit cases, and the results show that the trained actor-network can provide appropriate unitary transformations to obtain the fixed state.The quantum state generation problem is a major research goal of quantum control and quantum variational algorithms, which use iterative optimization methods to evolve the initial state to the target state. The Twin Delayed Deep Deterministic Policy (TD3) algorithm in reinforcement learning achieves high learning efficiency and better stability in continuous control tasks. Here, using the TD3, we propose a new quantum state preparation method that does not require case-by-case optimization, to find a suitable evolution path to obtain the desired state. Specifically, we input the initial state into the trained actor-network, which can output the parameters of the unitary gates step by step, thus gradually evolving the initial state to the fixed quantum state. According to the reversibility of the unitary transformation, we can obtain a sequence of unitary gates to evolve the fixed state to the desired state. To verify the effectiveness of the algorithm, we perform simulations for one-qubit, two-qubit, and four-qubit cases, and the results show that the trained actor-network can provide appropriate unitary transformations to obtain the fixed state.

Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and CyberneticsOct 1, 20231 citation

Reinforcement learning for quantum circuit optimization

Thomas Fösel, Murphy Yuezhen Niu, Florian Marquardt +1 more

Bulletin of the American Physical SocietyMar 16, 20210 citations

Optimizing Initial Qubit Mappings Under Fixed Gate Error Rates Using Deep Reinforcement Learning

Related papers

Optimizing Initial Qubit Mappings Under Fixed Gate Error Rates Using Deep Reinforcement Learning

Related papers