Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2407.16368 · Physica Scripta

Arbitrary quantum states preparation aided by deep reinforcement learning

Zhaowei Wang, Zhao-Ming Wang

Published Feb 26, 2025• 3 citations
arXivHTMLPDF

Abstract

Abstract The preparation of quantum states is essential in the realm of quantum information processing, and the development of efficient methodologies can significantly alleviate the strain on quantum resources. Under the framework of deep reinforcement learning (DRL), we integrate the initial and the target state information within the state preparation task together, so as to realize the control trajectory design between two arbitrary quantum states. Taking a semiconductor double quantum dots (DQDs) model as an example, our results demonstrate that the resulting control trajectories can effectively achieve arbitrary quantum state preparation (AQSP) for both single-qubit and two-qubit systems, with average fidelities of 0.9868 and 0.9556 for the test sets, respectively. For the DQDs, charge and nuclear noises will exist, thus decreases the average fidelity of AQSP. We have also incorporated noise amplitude as an input feature in the training process, leading to the development of noise-aware models. The control trajectories designed by these models can effectively suppress the influence of noise. Our research validates the effectiveness of DRL in quantum state preparation and offers solutions for multi-initial and multi-objective quantum control tasks, with potential for broader application in quantum control problems.

DOI
10.1088/1402-4896/adbabc

Related papers

Deep reinforcement learning for universal quantum state preparation via dynamic pulse control

Run-Hong He, Rui Wang, Shen-Shuang Nie +3 more

Abstract Accurate and efficient preparation of quantum state is a core issue in building a quantum computer. In this paper, we investigate how to prepare a certain single- or two-qubit target state from arbitrary initial states in semiconductor double quantum dots with only a few discrete control pulses by leveraging the deep reinforcement learning. Our method is based on the training of the network over numerous preparing tasks. The results show that once the network is well trained, it works for any initial states in the continuous Hilbert space. Thus repeated training for new preparation tasks is avoided. Our scheme outperforms the traditional optimization approaches based on gradient with both the higher efficiency and the preparation quality in discrete control space. Moreover, we find that the control trajectories designed by our scheme are robust against stochastic fluctuations within certain thresholds, such as the charge and nuclear noises.

arXiv:2012.00326•EPJ Quantum Technology•Dec 1, 2021•26 citations

Critical States Preparation With Deep Reinforcement Learning

Jia-Wen Yu, Yi-Ming Yu, Ke-Xiong Yan +4 more

The fast and efficient preparation of quantum critical states is a challenging yet crucial task for various quantum technologies. This difficulty is most particularly for systems near a quantum phase transition, where the closure of the energy gap fundamentally limits the timescale of adiabatic processes and thus precludes rapid state preparation. We propose a framework using deep reinforcement learning (DRL) to rapidly prepare quantum critical states, with broad extendibility to light-matter interaction systems. Specifically, a DRL agent optimizes a set of time-dependent control Hamiltonians to drive the system from an initial noncritical state to a target critical state within a finite time and over experimentally accessible parameter ranges. As a concrete application, we focus on the quantum Rabi model. The DRL-optimized time-dependent control Hamiltonian yield a final state with high-fidelity ($>0.999$) to the target critical state. The protocol can be readily extended to other quantum critical systems described by light-matter interaction models, such as quantum Dicke model. This investigation provides a powerful new framework for preparing and manipulating quantum critical states.

quant-pharXiv:2603.09135•Mar 11, 2026•0 citations

Machine-Learning-Assisted Pulse Design for State Preparation in a Noisy Environment

Zhaowei Wang, Hongyang Ma, Yun‐An Yan +2 more

High-precision quantum control is essential for quantum computing and quantum information processing. However, its practical implementation is challenged by environmental noise, which affects the stability and accuracy of quantum systems. In this paper, using machine learning techniques we propose a quantum control approach that incorporates environmental factors into the design of control schemes, improving the control fidelity in noisy environments. Specifically, we investigate arbitrary quantum state preparation in a two-level system coupled to a bosonic bath. We use both Deep Reinforcement Learning (DRL) and Supervised Learning (SL) algorithms to design specific control pulses that mitigate the noise. These two neural network (NN) based algorithm both have the advantage that the well trained NN can output the optimal pulse sequence for any environmental parameters. Comparing the performance of these two algorithms, our results show that DRL is more effective in low-noise environments due to its strong optimization capabilities, while SL provides greater stability and performs better in high-noise conditions. These findings highlight the potential of machine learning techniques to enhance the quantum control fidelity in practical applications.

arXiv:2508.20377•Aug 28, 2025•0 citations

Deep Reinforcement Learning With Reward Design for Quantum Control

Haixu Yu, Xudong Zhao

Deep reinforcement learning (DRL) has been recognized as a powerful tool in quantum physics, where DRL's reward design is nontrivial but crucial for quantum control tasks. To address the problem of over-reliance on human empirical knowledge to design DRL's rewards, we propose a DRL with a novel reward paradigm designed by the learning process information (DRL-LPI), where the learning process information (LPI) comprises the state information and the experiences. In DRL-LPI, the state information after being classified by a fidelity threshold, and the experiences are first stored simultaneously in the respective sequences, and this process is repeated until a similar-segment ends. Then, the stored state information is converted to the real value and used to design the reward value by applying a self-amplitude function. Next, the designed reward values are integrated with the stored experiences to compose transitions for DRL's training. Through comparisons to five representative reward schemes, the proposed DRL-LPI is evaluated on two typical quantum control tasks, i.e., the spin-(1/2) quantum state control and many-coupled qubits state control, and the experimental results show the superior learning efficiency and control performance of the proposed approach. More results show that DRL-LPI exhibits the ability to learn the control strategy with few control actions compared to stochastic gradient descent (SGD) and genetic algorithm (GA).

IEEE Transactions on Artificial Intelligence•Nov 28, 2022•27 citations

Control Hamiltonian selection for quantum state stabilization using deep reinforcement learning

Chunxiang Song, Yanan Liu, Daoyi Dong +1 more

Quantum state stabilization is a pivotal element in the realm of quantum control, forming the bedrock for various quantum tasks. To achieve the stabilization of a quantum state, it is imperative to formulate effective control channels (represented by control Hamiltonians) and devise the appropriate control signals. In this study, we introduce a novel approach, the selection of control Hamiltonians through Deep reinforcement learning (SCH-DRL), to address the challenge of control Hamiltonian selection in quantum control. Deep reinforcement learning (DRL) is employed to generate control signals corresponding to control Hamiltonians, and SCH-DRL utilizes these control signals to recognize a set of simple and efficient control Hamiltonians, depending on different target states. This approach not only provides a method for control Hamiltonian selection in quantum state stabilization but also unveils the untapped potential of DRL for a broad spectrum of applications in the field of quantum information. Through applications in two-qubit and three-qubit scenarios, we demonstrate how the SCH-DRL method adeptly selects the quantity of control Hamiltonians for achieving the desired stability of quantum states.

Chinese Control Conference (CCC)•Jul 28, 2024•0 citations

Auxiliary Task-Based Deep Reinforcement Learning for Quantum Control

Shumin Zhou, Hailan Ma, Sen Kuang +1 more

Due to its property of not requiring prior knowledge of the environment, reinforcement learning (RL) has significant potential for solving quantum control problems. In this work, we investigate the effectiveness of continuous control policies based on deep deterministic policy gradient. To achieve good control of quantum systems with high fidelity, we propose an auxiliary task-based deep RL (AT-DRL) for quantum control. In particular, we design an auxiliary task to predict the fidelity value, sharing partial parameters with the main network (from the main RL task). The auxiliary task learns synchronously with the main task, allowing one to extract intrinsic features of the environment, thus aiding the agent to achieve the desired state with high fidelity. To further enhance the control performance, we also design a guided reward function based on the fidelity of quantum states that enables gradual fidelity improvement. Numerical simulations demonstrate that the proposed AT-DRL can provide a good solution to the exploration of quantum dynamics. It not only achieves high task fidelities but also demonstrates fast learning rates. Moreover, AT-DRL has great potential in designing control pulses that achieve effective quantum state preparation.

arXiv:2302.14312•IEEE Transactions on Cybernetics•Jan 7, 2025•6 citations
Abstract The preparation of quantum states is essential in the realm of quantum information processing, and the development of efficient methodologies can significantly alleviate the strain on quantum resources. Under the framework of deep reinforcement learning (DRL), we integrate the initial and the target state information within the state preparation task together, so as to realize the control trajectory design between two arbitrary quantum states. Taking a semiconductor double quantum dots (DQDs) model as an example, our results demonstrate that the resulting control trajectories can effectively achieve arbitrary quantum state preparation (AQSP) for both single-qubit and two-qubit systems, with average fidelities of 0.9868 and 0.9556 for the test sets, respectively. For the DQDs, charge and nuclear noises will exist, thus decreases the average fidelity of AQSP. We have also incorporated noise amplitude as an input feature in the training process, leading to the development of noise-aware models. The control trajectories designed by these models can effectively suppress the influence of noise. Our research validates the effectiveness of DRL in quantum state preparation and offers solutions for multi-initial and multi-objective quantum control tasks, with potential for broader application in quantum control problems.
Abstract Accurate and efficient preparation of quantum state is a core issue in building a quantum computer. In this paper, we investigate how to prepare a certain single- or two-qubit target state from arbitrary initial states in semiconductor double quantum dots with only a few discrete control pulses by leveraging the deep reinforcement learning. Our method is based on the training of the network over numerous preparing tasks. The results show that once the network is well trained, it works for any initial states in the continuous Hilbert space. Thus repeated training for new preparation tasks is avoided. Our scheme outperforms the traditional optimization approaches based on gradient with both the higher efficiency and the preparation quality in discrete control space. Moreover, we find that the control trajectories designed by our scheme are robust against stochastic fluctuations within certain thresholds, such as the charge and nuclear noises.
The fast and efficient preparation of quantum critical states is a challenging yet crucial task for various quantum technologies. This difficulty is most particularly for systems near a quantum phase transition, where the closure of the energy gap fundamentally limits the timescale of adiabatic processes and thus precludes rapid state preparation. We propose a framework using deep reinforcement learning (DRL) to rapidly prepare quantum critical states, with broad extendibility to light-matter interaction systems. Specifically, a DRL agent optimizes a set of time-dependent control Hamiltonians to drive the system from an initial noncritical state to a target critical state within a finite time and over experimentally accessible parameter ranges. As a concrete application, we focus on the quantum Rabi model. The DRL-optimized time-dependent control Hamiltonian yield a final state with high-fidelity (>0.999>0.999>0.999) to the target critical state. The protocol can be readily extended to other quantum critical systems described by light-matter interaction models, such as quantum Dicke model. This investigation provides a powerful new framework for preparing and manipulating quantum critical states.
High-precision quantum control is essential for quantum computing and quantum information processing. However, its practical implementation is challenged by environmental noise, which affects the stability and accuracy of quantum systems. In this paper, using machine learning techniques we propose a quantum control approach that incorporates environmental factors into the design of control schemes, improving the control fidelity in noisy environments. Specifically, we investigate arbitrary quantum state preparation in a two-level system coupled to a bosonic bath. We use both Deep Reinforcement Learning (DRL) and Supervised Learning (SL) algorithms to design specific control pulses that mitigate the noise. These two neural network (NN) based algorithm both have the advantage that the well trained NN can output the optimal pulse sequence for any environmental parameters. Comparing the performance of these two algorithms, our results show that DRL is more effective in low-noise environments due to its strong optimization capabilities, while SL provides greater stability and performs better in high-noise conditions. These findings highlight the potential of machine learning techniques to enhance the quantum control fidelity in practical applications.
Deep reinforcement learning (DRL) has been recognized as a powerful tool in quantum physics, where DRL's reward design is nontrivial but crucial for quantum control tasks. To address the problem of over-reliance on human empirical knowledge to design DRL's rewards, we propose a DRL with a novel reward paradigm designed by the learning process information (DRL-LPI), where the learning process information (LPI) comprises the state information and the experiences. In DRL-LPI, the state information after being classified by a fidelity threshold, and the experiences are first stored simultaneously in the respective sequences, and this process is repeated until a similar-segment ends. Then, the stored state information is converted to the real value and used to design the reward value by applying a self-amplitude function. Next, the designed reward values are integrated with the stored experiences to compose transitions for DRL's training. Through comparisons to five representative reward schemes, the proposed DRL-LPI is evaluated on two typical quantum control tasks, i.e., the spin-(1/2) quantum state control and many-coupled qubits state control, and the experimental results show the superior learning efficiency and control performance of the proposed approach. More results show that DRL-LPI exhibits the ability to learn the control strategy with few control actions compared to stochastic gradient descent (SGD) and genetic algorithm (GA).
Quantum state stabilization is a pivotal element in the realm of quantum control, forming the bedrock for various quantum tasks. To achieve the stabilization of a quantum state, it is imperative to formulate effective control channels (represented by control Hamiltonians) and devise the appropriate control signals. In this study, we introduce a novel approach, the selection of control Hamiltonians through Deep reinforcement learning (SCH-DRL), to address the challenge of control Hamiltonian selection in quantum control. Deep reinforcement learning (DRL) is employed to generate control signals corresponding to control Hamiltonians, and SCH-DRL utilizes these control signals to recognize a set of simple and efficient control Hamiltonians, depending on different target states. This approach not only provides a method for control Hamiltonian selection in quantum state stabilization but also unveils the untapped potential of DRL for a broad spectrum of applications in the field of quantum information. Through applications in two-qubit and three-qubit scenarios, we demonstrate how the SCH-DRL method adeptly selects the quantity of control Hamiltonians for achieving the desired stability of quantum states.
Due to its property of not requiring prior knowledge of the environment, reinforcement learning (RL) has significant potential for solving quantum control problems. In this work, we investigate the effectiveness of continuous control policies based on deep deterministic policy gradient. To achieve good control of quantum systems with high fidelity, we propose an auxiliary task-based deep RL (AT-DRL) for quantum control. In particular, we design an auxiliary task to predict the fidelity value, sharing partial parameters with the main network (from the main RL task). The auxiliary task learns synchronously with the main task, allowing one to extract intrinsic features of the environment, thus aiding the agent to achieve the desired state with high fidelity. To further enhance the control performance, we also design a guided reward function based on the fidelity of quantum states that enables gradual fidelity improvement. Numerical simulations demonstrate that the proposed AT-DRL can provide a good solution to the exploration of quantum dynamics. It not only achieves high task fidelities but also demonstrates fast learning rates. Moreover, AT-DRL has great potential in designing control pulses that achieve effective quantum state preparation.