DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search
On the map: World models → Latent dynamics models and model-based RL
Abstract (arXiv)
Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly invokes a variational quantum eigensolver (VQE) after each gate addition even though circuit transitions and action legality are known. DreamQAS preserves these exact dynamics and learns only expensive post-VQE feedback through a recurrent ensemble that predicts a frontier-relative feedback score without requiring the exact ground-state energy, enabling uncertainty-controlled multi-step imagination. Under a common 15,000-episode budget and frozen evaluation, DreamQAS has the lowest reported mean error among RL methods on all five main molecular tasks. At fine-error targets reached by all seeds of DreamQAS and a matched non-imaginative control, it uses 1.6-2.0 times fewer real VQE calls on four tasks. Holding LiH-4q feedback-model weights fixed, its imagined-policy actor attains 0.073 mHa, versus 4.280 mHa and 4.434 mHa for greedy and beam deployment. Learned-transition and end-to-end predictor controls further show that preserving exact circuit structure and using feedback through policy learning are both important. Counterfactual action-ranking improves throughout training on all five probed tasks, while ensemble disagreement improves risk-coverage over random rejection on three tasks. DreamQAS therefore learns decision-useful feedback for QAS without modeling already-known circuit dynamics or requiring the exact ground-state energy.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Latent dynamics models and model-based RL, one of 11 directions in World models. Builds on 16 of its 42 references that are in the map. First posted on arXiv 31 Jul 2026.
Builds on
16 of 42 references.
Closest ancestors · 4
Same direction, newest first
- 2019Dream to Control: Learning Behaviors by Latent Imagination3 Dec
- 2019When to Trust Your Model: Model-Based Policy Optimization19 Jun
- 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models30 May
- 2018World Models27 Mar
Other references · 12
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2017Selective Classification for Deep Neural Networkscited by 852
- 2020MOPO: Model-based Offline Policy Optimizationcited by 636
- 2020MOReL : Model-Based Offline Reinforcement Learningcited by 590
- 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 219
- 2020Quantum circuit architecture search for variational quantum algorithmscited by 82
- 2021Reinforcement learning for optimization of variational quantum circuit architecturescited by 77
- 2024Curriculum reinforcement learning for quantum architecture search under hardware errorscited by 37
- 2024Quantum Architecture Search: A Surveycited by 32
- 2024Reinforcement learning-based architecture search for quantum machine learningcited by 9
- 2025BenchRL-QAS: Benchmarking reinforcement learning algorithms for quantum architecture searchcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Reinforcement learning-assisted quantum architecture search for variational quantum algorithms
- 2025TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search
- 2024KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search
- 2025Quantum Architecture Search for Solving Quantum Machine Learning Tasks
- 2026Generative Replay Mitigates Sample Starvation in Quantum Architecture Search
- 2025Separating Ansatz Discovery from Deployment on Larger Problems: Reinforcement Learning for Modular Circuit Design
- 2024Differentiable Quantum Architecture Search in Asynchronous Quantum Reinforcement Learning
- 2026Reinforcement Learning for Quantum Technology