Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning

• URL: http://arxiv.org/abs/2512.14726v1
• Date: Tue, 09 Dec 2025 16:47:37 GMT
• Title: Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning
• Authors: Abraham Itzhak Weinberg,
• Abstract summary: We introduce the Quantum Decision Transformer (QDT), a novel architecture incorporating quantum-inspired computational mechanisms.<n>Our approach integrates two core components: Quantum-Inspired Attention with entanglement operations that capture non-local feature correlations, and Quantum Feedforward Networks with multi-path processing and learnable interference for adaptive computation.
• Score: 0.2538209532048867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Offline reinforcement learning enables policy learning from pre-collected datasets without environment interaction, but existing Decision Transformer (DT) architectures struggle with long-horizon credit assignment and complex state-action dependencies. We introduce the Quantum Decision Transformer (QDT), a novel architecture incorporating quantum-inspired computational mechanisms to address these challenges. Our approach integrates two core components: Quantum-Inspired Attention with entanglement operations that capture non-local feature correlations, and Quantum Feedforward Networks with multi-path processing and learnable interference for adaptive computation. Through comprehensive experiments on continuous control tasks, we demonstrate over 2,000\% performance improvement compared to standard DTs, with superior generalization across varying data qualities. Critically, our ablation studies reveal strong synergistic effects between quantum-inspired components: neither alone achieves competitive performance, yet their combination produces dramatic improvements far exceeding individual contributions. This synergy demonstrates that effective quantum-inspired architecture design requires holistic co-design of interdependent mechanisms rather than modular component adoption. Our analysis identifies three key computational advantages: enhanced credit assignment through non-local correlations, implicit ensemble behavior via parallel processing, and adaptive resource allocation through learnable interference. These findings establish quantum-inspired design principles as a promising direction for advancing transformer architectures in sequential decision-making, with implications extending beyond reinforcement learning to neural architecture design more broadly.

Related papers

• Quantum LEGO Learning: A Modular Design Principle for Hybrid Artificial Intelligence [63.39968536637762]
  We introduce Quantum LEGO Learning, a learning framework that treats classical and quantum components as reusable, composable learning blocks.<n>Within this framework, a pre-trained classical neural network serves as a frozen feature block, while a VQC acts as a trainable adaptive module.<n>We develop a block-wise generalization theory that decomposes learning error into approximation and estimation components.
  arXiv  Detail & Related papers  (2026-01-29T14:29:21Z)
• Benchmarking Quantum Data Center Architectures: A Performance and Scalability Perspective [13.628992375229247]
  We study the impact of four representative quantum data-center architectures on distributed quantum circuit execution latency, resource contention, and scalability.<n>Our results show that distributed quantum performance is jointly shaped by topology, scheduling policies, and physical-layer parameters.
  arXiv  Detail & Related papers  (2026-01-04T03:48:02Z)
• Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning [58.533203990515034]
  Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL)<n>We show that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements.<n>We finally distill these insights into Module-Specific Training (MST), a practical framework that exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.
  arXiv  Detail & Related papers  (2025-10-14T03:03:08Z)
• Reinforcement Learning for Quantum Network Control with Application-Driven Objectives [53.03367590211247]
  Dynamic programming and reinforcement learning offer promising tools for optimizing control strategies.<n>We propose a novel RL framework that directly optimize non-linear, differentiable objective functions.<n>Our work comprises the first step towards non-linear objective function optimization in quantum networks with RL, opening a path towards more advanced use cases.
  arXiv  Detail & Related papers  (2025-09-12T18:41:10Z)
• Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning [0.0]
  Quantum Graph Attention Network (QGAT) is a hybrid graph neural network that integrates variational quantum circuits into the attention mechanism.<n>We show QGAT's effectiveness in capturing complex structural dependencies and improved generalization in inductive scenarios.<n>Experiments confirm that quantum embedding enhances robustness against feature and structural noise, suggesting advantages in handling real-world noisy data.
  arXiv  Detail & Related papers  (2025-08-25T03:25:48Z)
• End-to-End Analysis of Charge Stability Diagrams with Transformers [0.7570270968488804]
  Transformer models and end-to-end learning frameworks are rapidly revolutionizing the field of artificial intelligence.<n>In this work, we apply object detection transformers to analyze charge stability diagrams in semiconductor quantum dot arrays.<n>We show that it surpasses convolutional neural networks in performance on three different spin qubit architectures.
  arXiv  Detail & Related papers  (2025-08-21T16:54:22Z)
• Stackelberg Coupling of Online Representation Learning and Reinforcement Learning [45.70357546589222]
  We introduce SCORER, a framework for value-based RL that views representation and Q-learning as two strategic agents in a hierarchical game.<n>Our proposed SCORER framework leads to a bi-level optimization problem whose solution is approximated by a two-timescale algorithm.
  arXiv  Detail & Related papers  (2025-08-10T18:36:54Z)
• A Survey of Quantum Transformers: Architectures, Challenges and Outlooks [82.4736481748099]
  Quantum Transformers integrate the representational power of classical Transformers with the computational advantages of quantum computing.<n>Since 2022, research in this area has rapidly expanded, giving rise to diverse technical paradigms and early applications.<n>This paper presents the first comprehensive, systematic, and in-depth survey of quantum Transformer models.
  arXiv  Detail & Related papers  (2025-04-04T05:40:18Z)
• UDiTQC: U-Net-Style Diffusion Transformer for Quantum Circuit Synthesis [13.380226276791818]
  Current diffusion model approaches based on U-Net architectures, while promising, encounter challenges related to computational efficiency and modeling global context.<n>We propose UDiT,a novel U-Net-style Diffusion Transformer architecture, which combines U-Net's strengths in multi-scale feature extraction with the Transformer's ability to model global context.
  arXiv  Detail & Related papers  (2025-01-24T15:15:50Z)
• Variational Quantum Circuit Decoupling [1.0445957451908694]
  Decoupling systems into independently evolving components has a long history of simplifying seemingly complex systems. We apply this approach to quantum circuit synthesis - the task of discovering quantum circuit implementations of target unitary dynamics.
  arXiv  Detail & Related papers  (2024-06-09T03:01:50Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• Realization of arbitrary doubly-controlled quantum phase gates [62.997667081978825]
  We introduce a high-fidelity gate set inspired by a proposal for near-term quantum advantage in optimization problems. By orchestrating coherent, multi-level control over three transmon qutrits, we synthesize a family of deterministic, continuous-angle quantum phase gates acting in the natural three-qubit computational basis.
  arXiv  Detail & Related papers  (2021-08-03T17:49:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.