Work

Multi-Armed Bandits and Quantum Channel Oracles

Year: 2025

Type: article

Abstract: Multi-armed bandits are one of the theoretical pillars of reinforcement learning. Recently, the investigation of quantum algorithms for multi-armed bandit problems was started, and it was found that a quadratic speed-up (in query complexity) is possible when the arms and the randomness of the rewards of the arms can be queried in superposition. Here we introduce further bandit models where we only have limited access to the randomness of the rewards, but we can still query the arms in superposition. We show that then the query complexity is the same as for classical algorithms. This generalizes the prior result that no speed-up is possible for unstructured search when the oracle has positive failure probability.

Source: Quantum

DOI: 10.22331/q-2025-03-25-1672

Authors: Simon Buchholz, Jonas M. Kübler, Bernhard Schölkopf

Institution: Max Planck Institute for Intelligent Systems

Language: English

Topic: Quantum Computing Algorithms and Architecture

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $215

Funder: Deutsche Forschungsgemeinschaft