Digital Twin-Driven MADRL Approaches for Communication-Computing-Control Co-Optimization
Bibliographic record
Abstract
The unpredictability of network environments, limited edge resources, and the high complexity of collaborative policies are significantly hindering the development of the Industrial Internet of Things (IIoT). These challenges are particularly pronounced in healthcare, where high-priority, delay-sensitive medical tasks and large-scale personalized services face substantial obstacles. To address these challenges, this paper proposes the Self-Attention Enhanced QMIX with Multi-Pass Multi-Task Execution (SAE-MT-QMIX) algorithm, aimed at optimizing communication and computing resource allocation as well as task offloading strategies. By leveraging Digital Twin (DT) support, the algorithm achieves collaborative optimization of communication, computing, and control within the Internet of Medical Things (IoMT), significantly enhancing the quality of service for massive personalized applications. The algorithm adopts a distributed execution and centralized training framework: the distributed execution component uses the Multi-Pass Multi-Task Deep Q-Network (MPMT-DQN) algorithm to handle the complexity of parameterized action spaces in multi-task scenarios, while the centralized training component employs the Self-Attention Enhanced QMIX (SAE-QMIX) algorithm to dynamically optimize credit assignment across multiple users. Simulation results demonstrate that SAE-MT-QMIX significantly reduces delay and energy consumption compared to baseline methods. It ensures effective optimization of communication, computing, and control in dynamic IoMT, efficiently addressing diverse demands and tasks while enhancing service quality and system adaptability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".