SymQNet: fast adaptive Hamiltonian learning via amortized acquisition
SymQNet provides a full‑stack Python toolkit for low‑latency adaptive Hamiltonian learning on spin‑chain simulators, using reinforcement‑learning policies and a belief‑VAE. It includes a simulator, particle‑filter, training scripts, pretrained checkpoints, and evaluation baselines, enabling researchers to reproduce and extend the published results. The package is aimed at quantum‑computing researchers and ML engineers needing a ready‑to‑run benchmark for adaptive quantum control. Its modular design and ready‑made pipelines make it more practical than scattered research notebooks.
View on GitHub →YTomar79/symqnet_quantum