This paper introduces the QDQN-DPER framework to enhance the efficiency of quantum reinforcement learning (QRL) in solving sequential decision tasks. The framework incorporates prioritized experience replay, asynchronous training and novel matrix loss into the training algorithm to reduce the high sampling complexities. Numerical simulations demonstrate that QDQN-DPER outperforms the baseline distributed quantum Q-learning with the same model architecture. The proposed framework holds potential for more complex tasks while maintaining training efficiency.
This paper introduces the QDQN-DPER framework to enhance the efficiency of quantum reinforcement learning (QRL) in solving sequential decision tasks. The framework incorporates prioritized experience replay, asynchronous training and novel matrix loss into the training algorithm to reduce the high sampling complexities. Numerical simulations demonstrate that QDQN-DPER outperforms the baseline distributed quantum Q-learning with the same model architecture. The proposed framework holds potential for more complex tasks while maintaining training efficiency.
Reinforcement learning (RL) encounters significant challenges related to scalability and computational efficiency, particularly in complex decision-making environments. Traditional RL algorithms often struggle with large-scale tasks, necessitating innovative approaches to enhance adaptability and performance. The quantum circuit-based priority replay (QCPR) algorithm was introduced in this study, leveraging quantum-inspired techniques to enhance learning efficiency and decision-making quality through quantum computing (QC). The QCPR algorithm implements two key mechanisms for prioritizing experiences: the magnitude and direction (MaDi) based priority, which assesses the significance and directionality of experiences, and QCPR-specific methods that ensure efficient experience replay. These mechanisms are seamlessly integrated into the Q-learning (QL) framework to optimize the RL process for superior performance. QCPR was evaluated against four well-established RL algorithms-QL, deep Q-networks (DQN), prioritized experience replay (PER), and dueling DQN (DDQN)-using standard decision-making benchmarks. The algorithm was further tested in various simulation and real-world environments, including Atari games, Qiskit integration, and Raspberry Pi hardware and software setups. These evaluations demonstrated QCPR’s adaptability and robustness, showcasing its capability for dynamic, large-scale applications. The results revealed that QCPR significantly outperforms its counterparts across key performance metrics, including accuracy, precision, recall, F1-score, and cumulative rewards. Specifically, QCPR achieved a 15.29% improvement in accuracy over QL, a 9.98% increase over DQN, a 6.33% improvement over PER, and an 8.23% enhancement over DDQN. This study highlights the potential of quantum-inspired approaches to advance RL, offering scalable and efficient solutions for complex decision-making tasks.
Quantum reinforcement learning (QRL) has emerged as a framework to solve sequential decision-making tasks, showcasing empirical quantum advantages. A notable development is through quantum recurrent neural networks (QRNNs) for memory-intensive tasks such as partially observable environments. However, QRL models incorporating QRNN encounter challenges such as inefficient training of QRL with QRNN, given that the computation of gradients in QRNN is both computationally expensive and time-consuming. This work presents a novel approach to address this challenge by constructing QRL agents utilizing QRNN-based reservoirs, specifically employing quantum long short-term memory (QLSTM). QLSTM parameters are randomly initialized and fixed without training. The model is trained using the asynchronous advantage actor-critic (A3C) algorithm. Through numerical simulations, we validate the efficacy of our QLSTM-Reservoir RL framework. Its performance is assessed on standard benchmarks, demonstrating comparable results to a fully trained QLSTM RL model with identical architecture and training settings.
Recent advances in quantum computing (QC) and machine learning (ML) have drawn significant attention to the development of quantum machine learning (QML). Reinforcement learning (RL) is one of the ML paradigms which can be used to solve complex sequential decision making problems. Classical RL has been shown to be capable to solve various challenging tasks. However, RL algorithms in the quantum world are still in their infancy. One of the challenges yet to solve is how to train quantum RL in the partially observable environments. In this paper, we approach this challenge through building QRL agents with quantum recurrent neural networks (QRNN). Specifically, we choose the quantum long short-term memory (QLSTM) to be the core of the QRL agent and train the whole model with deep Q-learning. We demonstrate the results via numerical simulations that the QLSTM-DRQN can solve standard benchmark such as Cart-Pole with more stable and higher average scores than classical DRQN with similar architecture and number of model parameters.
Recent advances in quantum computing (QC) and machine learning (ML) have drawn significant attention to the development of quantum machine learning (QML). Reinforcement learning (RL) is one of the ML paradigms which can be used to solve complex sequential decision making problems. Classical RL has been shown to be capable to solve various challenging tasks. However, RL algorithms in the quantum world are still in their infancy. One of the challenges yet to solve is how to train quantum RL in the partially observable environments. In this paper, we approach this challenge through building QRL agents with quantum recurrent neural networks (QRNN). Specifically, we choose the quantum long short-term memory (QLSTM) to be the core of the QRL agent and train the whole model with deep Q-learning. We demonstrate the results via numerical simulations that the QLSTM-DRQN can solve standard benchmark such as Cart-Pole with more stable and higher average scores than classical DRQN with similar architecture and number of model parameters.
This paper explores the application of Quantum-Enhanced Reinforcement Learning (QRL) to robotics, aiming to accelerate learning speeds and enable more intelligent decision-making in complex environments. Traditional reinforcement learning algorithms often struggle with scalability and convergence, particularly when dealing with high-dimensional state spaces and complex environments. Quantum computing offers the potential to overcome these limitations by leveraging quantum mechanics to perform computations that are intractable for classical computers. We propose a novel QRL framework that utilizes quantum-enhanced reinforcement learning to improve exploration, adaptation, and overall performance. The core mechanism involves employing quantum circuits to represent and manipulate the state space, facilitating more efficient learning and potentially uncovering novel strategies. This research investigates the feasibility and potential impact of QRL on robotic control, focusing on scenarios requiring rapid adaptation and robust decision-making in dynamic environments. We present preliminary results demonstrating the efficacy of our approach in a simulated robotic task involving navigation and obstacle avoidance.
A metaverse is composed of a physical-space and virtual-space, with the aim of having users in both the virtual reality and the real world experience. Prioritization is essential, but it is not straight-forwarded due to the limitation of computing resources in real-world, making it impossible to synchronize all data. Therefore, it is crucial to allocate resources based on regional preferences in physical-space and content preferences of users in virtual-space. The referencing system consists of two-stage sub-computations, (i) spatial-prioritization for more data gathering under the consideration of avatar-popularity one top of physical-space and (ii) temporal-prioritization for virtual-space rendering under the avatar-popularity. Both prioritization tasks are combinatorics problems and are well-known NP-hard. The problem scale is also large, making it difficult to solve within given times. The classical deep learning cannot be the solution. Quantum-based learning algorithms can be the potential solutions due to high-performance computing capabilities, because a small number of qubits can represent an exponentially large amount of information. On top of these advantages, an improved quantum reinforcement learning (QRL) algorithm is proposed for reducing the control dimensions into a logarithmic scale. We corroborate that our proposed QRL-based algorithm for low-dimensional spatio-temporal prioritization improves convergence and performance.