Reproduce “Quantum exploration algorithms for multi-armed bandits” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Daochen Wang, Xuchen You, Tongyang Li, Andrew M. Childs
The quantum algorithm identifies a unique best arm with fixed confidence using coherent oracle access, which encodes reward probabilities in amplitudes. It estimates and filters arms in stages, then amplifies the best-arm state. Its query bound scales as the square root of H, versus H classically; a matching lower bound holds only when biases are bounded away from zero and one.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.