mlsanityData to 7 Oct 2026

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

arXiv 2512.14726 ↗First posted 9 Dec 2025cs.LG cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Decision transformers and sequence modeling

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data. Builds on 56 of its 84 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

56 of 84 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Dichotomy of Control: Separating What You Can Control from What You Cannot24 Oct
  2. 2022Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL8 Sep
  3. 2022Online Decision Transformer11 Feb
  4. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problem3 Jun
  5. 2021Decision Transformer: Reinforcement Learning via Sequence Modeling2 Jun

Other references · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2016Layer Normalizationcited by 5,579
  10. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  11. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  12. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
38 more
  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  2. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  8. 2016OpenAI Gymcited by 1,684
  9. 2020Rethinking Attention with Performerscited by 1,584
  10. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  11. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  12. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  13. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  14. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  15. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  16. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 833
  17. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  18. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  19. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  20. 2019Behavior Regularized Offline Reinforcement Learningcited by 654
  21. 2016Deep Exploration via Bootstrapped DQNcited by 518
  22. 2017Progressive Neural Architecture Searchcited by 483
  23. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  24. 2017Deep & Cross Network for Ad Click Predictionscited by 392
  25. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  26. 2019Parameterized quantum circuits as machine learning modelscited by 330
  27. 2020Synthesizer: Rethinking Self-Attention in Transformer Modelscited by 204
  28. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
  29. 2015Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approachcited by 162
  30. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  31. 2018Differentiable Learning of Quantum Circuit Born Machinecited by 90
  32. 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
  33. 2021A Review on Graph Neural Network Methods in Financial Applicationscited by 77
  34. 2018Continuous-variable quantum neural networkscited by 74
  35. 2018A quantum-inspired classical algorithm for recommendation systemscited by 70
  36. 2016Quantum Recommendation Systemscited by 69
  37. 2020Counterfactual Credit Assignment in Model-Free Reinforcement Learningcited by 60
  38. 2018Unsupervised Predictive Memory in a Goal-Directed Agentcited by 54

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Improved Offline Reinforcement Learning via Quantum Metric Encoding
  2. 2025PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs
  3. 2025Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
  4. 2026QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling
  5. 2026Variational Quantum Circuit-Based Reinforcement Learning for Dynamic Portfolio Optimization
  6. 2026DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search
  7. 2025Quantum Circuit Reasoning Models: A Variational Framework for Differentiable Logical Inference
  8. 2025A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model