We present a machine learning framework to study the dynamics of entropy vectors and quantum resources, including entanglement and magic, focusing on violations of entropy inequalities. Using a reinforcement learning agent formulated as a Markov decision process, we identify quantum circuits that optimally navigate the entropy vector space to generate violations of Ingleton's inequality. We complement this approach with a classical optimization algorithm to produce arbitrary numbers of Ingleton-violating states, with tunable degrees of violation, and empirically determine the maximal attainable violation for Ingleton's inequality. Our analysis reveals characteristic patterns of quantum resources that accompany Ingleton violation. A comprehensive statistical analysis shows that Ingleton-violating states occupy sharply-defined, isolated regions of the Hilbert space, and are extremely rare. Together, these results establish a unified computational toolkit for studying entropy vector dynamics, tracking quantum resource evolution, and engineering circuits with controlled information-theoretic features.
We present a machine learning framework to study the dynamics of entropy vectors and quantum resources, including entanglement and magic, focusing on violations of entropy inequalities. Using a reinforcement learning agent formulated as a Markov decision process, we identify quantum circuits that optimally navigate the entropy vector space to generate violations of Ingleton's inequality. We complement this approach with a classical optimization algorithm to produce arbitrary numbers of Ingleton-violating states, with tunable degrees of violation, and empirically determine the maximal attainable violation for Ingleton's inequality. Our analysis reveals characteristic patterns of quantum resources that accompany Ingleton violation. A comprehensive statistical analysis shows that Ingleton-violating states occupy sharply-defined, isolated regions of the Hilbert space, and are extremely rare. Together, these results establish a unified computational toolkit for studying entropy vector dynamics, tracking quantum resource evolution, and engineering circuits with controlled information-theoretic features.
Abstract We present a machine learning framework to study the dynamics of entropy vectors and quantum resources, including entanglement and magic, with a focus on violations of entropy inequalities. In particular, we investigate Ingleton’s inequality, which is satisfied by all stabilizer and holographic quantum states. We first prove that violation is impossible for pure states of five qubits or fewer, establishing six qubits as the minimal system size required to cross the Ingleton boundary. Using a reinforcement learning agent formulated as a Markov decision process, we identify quantum circuits that navigate entropy vector space to generate Ingleton-violating states. Complementing this approach with classical optimization, we construct large families of violating states with tunable degrees of violation and empirically determine the maximal attainable violation. Our analysis reveals a sharp resource transition: violation requires substantial total quantum magic but only modest non-local magic, and occurs in statistically rare, sharply-defined regions of Hilbert space. Together, these results establish a unified computational toolkit for probing entropy cone boundaries, tracking quantum resource evolution, and engineering circuits with controlled information-theoretic features.
This chapter develops quantum reinforcement learning (QRL) as a principled extension of classical reinforcement learning (RL) into the quantum domain. Building on the standard Markov decision process framework, it shows how policies and value functions can be represented by quantum states and parameterized quantum circuits, with action probabilities arising from Born-rule measurement statistics and value estimates obtained from expectation values of observables. In this formulation, RL is preserved at the algorithmic level while its representational substrate is shifted from classical vector spaces to Hilbert space. The chapter emphasizes variational quantum circuits as the practical backbone of near-term QRL and analyzes how encoding strategies, entanglement structure, and measurement choices shape expressive power and trainability. It also examines quantum-enhanced exploration, showing how stochasticity emerges intrinsically from measurement rather than from externally injected noise. Policy-gradient and value-based approaches are compared, with particular attention to measurement cost, optimization stability, and near-term hardware suitability. This chapter further discusses quantum environments, sample-efficiency considerations, and hands-on implementations such as the quantum multi-armed bandit and quantum grid-world. Together, these topics establish QRL as a rigorous and practically grounded framework for studying sequential decision-making, control, and exploration in the quantum setting.
Abstract This work introduces a novel hybrid quantum-classical machine learning framework in which a Reinforcement Learning (RL) agent autonomously constructs quantum circuits to optimize kernels for a Quantum Support Vector Classifier (QSVC). Unlike traditional approaches that rely on fixed or manually designed quantum feature maps, the proposed method employs a Deep Q-Network (DQN) agent to dynamically select quantum gates and their parameters. These configurations define a parameterized quantum circuit whose fidelity-based kernel is used to perform classification tasks. The RL agent is trained to maximize classification accuracy by interacting with an environment that evaluates circuit performance. Experiments conducted on a realistic and potentially biased educational dataset demonstrate that the RL-optimized QSVC outperforms both classical SVC and standard QSVC baselines in terms of accuracy and fairness. Furthermore, SHAP-based explainability analysis reveals a reduction in model bias, suggesting improved interpretability and robustness. This study highlights the potential of reinforcement learning for automated quantum circuit design and kernel optimization in quantum machine learning.
This paper explores the application of Deep Reinforcement Learning (DRL) for optimizing quantum resource allocation in quantum computing. Traditional quantum resource allocation often relies on manual design and expert knowledge, which can be computationally expensive and limit scalability. We propose a novel framework utilizing DRL to automate this process, learning optimal strategies for allocating quantum resources (qubits, gates, and time) to maximize the performance of quantum algorithms. The core of our approach involves constructing a DRL model where the agent learns to make decisions regarding resource allocation based on the current state of the quantum system and the desired algorithm outcome. We define a state space representing the quantum system's configuration, action space encompassing various resource allocation options, and a reward function that reflects the algorithm's success. Through this framework, we aim to significantly enhance the efficiency and performance of quantum computations. This work presents a foundational approach, paving the way for more sophisticated DRL-based quantum resource allocation strategies.
Quantum networks depend critically on the efficient management of inherently unstable quantum resources, primarily entanglement. Traditional resource allocation methods often fail to account for the complex, dynamic trade-offs between entanglement distribution distance, fidelity, and decoherence, leading to significant wastage and underutilization. This paper studies the quantum resource allocation problem as a machinelearning optimization problem. We compare two distinct dynamic solvers: a Genetic Algorithm-based solver (Q-GA) and a Deep Reinforcement Learning-based solver (Q-DRL) in their ability to optimize resource allocation and address the resource allocation optimization framework. The Q-GA evolves a population of allocation strategies over time, whereas the Q-DRL agent learns a policy to make real-time distribution decisions. Our comparative analysis focuses on a multi-objective function designed to maximize the successful delivery of entangled pairs and their fidelity, while minimizing resource wastage due to decoherence, operational noise, the probabilistic nature of entanglement generation, and swapping operations. The study shows that in a variety of quantum resource allocation environments, both ML-based approaches significantly outperform conventional static heuristics. Notably, the Q-DRL solver exhibits superior adaptability to network dynamics, achieving a higher success rate and reduced resource wastage than the Q-GA. These findings establish their efficacy as a robust solution for the next-generation quantum resource allocation management.
As the number of qubits in a sensor increases, the complexity of designing and controlling the quantum circuits grows exponentially. Manually optimizing these circuits becomes infeasible. Optimizing entanglement distribution in large-scale quantum circuits is critical for enhancing the sensitivity and efficiency of quantum sensors (Yi, in Quantum Sci Technol, 045001, 2022, Thomas et al, in 2021). This paper presents an engineering integration of reinforcement learning with tensor-network-based simulation (MPS) for scalable circuit optimization for optimizing quantum sensor circuits with up to 60 qubits. To enable efficient simulation and scalability, we adopt tensor network methods—specifically, the Matrix Product State (MPS) representation—instead of traditional state vector or density matrix approaches. Our reinforcement learning agent learns to restructure circuits to maximize Quantum Fisher Information (QFI) and entanglement entropy while reducing gate counts and circuit depth. Experimental results show consistent improvements, with QFI values approaching 1, entanglement entropy in the 0.8–1.0 range, and up to 90% reduction in depth and gate count. These results highlight the potential of combining quantum machine learning and tensor networks to optimize complex quantum circuits under realistic constraints.