Research map / Probabilistic and scientific modeling / Molecules and proteins
Reinforcement learning for optimization of variational quantum circuit architectures
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use RL global COBYLA instead of HE | LiH VQE ansatz construction · LiH, 6 qubits, 2.2 Å | avg depth: 17 -> 14 | Helped |
| Use RL global COBYLA instead of HE | LiH VQE ansatz construction · LiH, 6 qubits, 2.2 Å | avg number of gates: 63 -> 36 | Helped |
| Use RL global COBYLA instead of UCCSD | LiH VQE ansatz construction · LiH, 6 qubits, 2.2 Å | avg depth: 377 -> 14 | Helped |
| Use RL global COBYLA instead of UCCSD | LiH VQE ansatz construction · LiH, 6 qubits, 2.2 Å | avg number of gates: 610 -> 36 | Helped |
| Use a fixed chemical-accuracy threshold rather than moving-threshold curriculum (ablation) | RL ansatz construction · LiH, 6 qubits | chemical accuracy success | Hurt |
| Use global angle optimization rather than local optimization (ablation) | RL ansatz construction · LiH, 4 qubits, 3.4 Å | successful trials: 2 out of 10; 3 out of 10 -> every trial | Helped |
| Use local Rotosolve rather than global optimization (ablation) | RL ansatz construction · LiH, 4 qubits | circuit depth versus HE | Hurt |
| Use COBYLA rather than Rotosolve (ablation) | RL ansatz construction · LiH, 4 qubits | circuit depth and gate count | Mixed |
| Use a rough lower-bound energy estimate instead of the exact ground-state energy (ablation) | Moving-threshold RL · LiH, 4 qubits, 2.2 Å | chemical accuracy | No clear effect |
Closest papers by meaning
- Curriculum reinforcement learning for quantum architecture search under hardware errors (ICLR 2024 · similarity 0.91)
- TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search (NeurIPS 2025 · similarity 0.89)
- Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms (AAAI 2025 · similarity 0.89)
- TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE (NeurIPS 2025 · similarity 0.88)
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization (NeurIPS 2025 · similarity 0.88)
- Training-Free Quantum Architecture Search (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.