メニュー
Q-DASC methodology for safe deployment of variational quantum circuit policies in physics-constrained control systems, with certified classical safety layers that handle model misspecification.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/hiyenwong/ai_collection --skill q-dasc-safe-quantum-controlコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis.
Physics-aware end-to-end deep reinforcement learning methodology for quadcopter control with actuator dynamics modeling.
Reinforced Dreamer methodology for asymmetric reinforcement learning using latent guidance to improve world model representations and behaviors in model-based RL.
SOC 職業分類に基づく
SKILL.md を表示中
| name | q-dasc-safe-quantum-control |
| description | Q-DASC methodology for safe deployment of variational quantum circuit policies in physics-constrained control systems, with certified classical safety layers that handle model misspecification. |
Q-DASC (Discrepancy-Attributed Safe Quantum Control) methodology for deploying variational quantum circuit (VQC) policies in safety-critical control systems. Wraps quantum policies with certified classical safety layers that discover misspecified operating regimes, repair local thermal gains, and project quantum schedules onto comfort-feasible sets with false-discovery-rate control. Reduces comfort violation from 26% to 0.02% on BOPTEST building emulators. (arXiv: 2606.28834)
Variational quantum circuits offer compact policy classes for control, but inherit a deployment weakness: when the model is locally wrong, a policy that appears safe can violate real-world constraints. Q-DASC addresses this by wrapping the VQC policy with a certified classical safety layer.
The final safety certificate is produced by classical projection, making comfort feasibility invariant to finite-shot and depolarizing read-out noise. This means the safety guarantee holds even on noisy quantum hardware (NISQ era).
Given: VQC policy π_θ(x) producing control action u
Safety Layer: Project u onto feasible set C_repair
u_safe = argmin_{v ∈ C_repair} ||v - u||²
Where C_repair is constructed from:
- FDR-controlled regime identification
- Shrinkage-repaired local thermal gains
- Physical constraint bounds
Residual violations are classified:
When deploying a variational quantum circuit controller in a safety-critical system:
When operating in unknown or changing environments:
When deploying on noisy quantum hardware:
Define the control task, constraints, and available system model. Identify safety-critical constraints that must never be violated.
Train a variational quantum circuit policy on the system model using standard RL or optimization methods.
At each control step:
Track violation attribution statistics to understand whether issues stem from policy quality, model accuracy, or physical infeasibility.
If violations persist after projection:
If FDR control is too conservative:
This is a class-level methodology skill for safe quantum control deployment, not paper-specific. The approach transfers to EnergyPlus heating/cooling benchmarks and real hospital air-handling-unit data.