Recent progress on building quantum computers [1] envisages wide applications of quantum algorithms in the near future. With the advantage of quantum computer, one can speed up not only fundamental algorithms, e.g., unstructured search [6] and factoring [11], but recent machine learning algorithms [3] as well. In this paper, we study the quantum speedup on a canonical task of reinforcement learning-best arm identification in multi-armed bandits.
Recent progress on building quantum computers [1] envisages wide applications of quantum algorithms in the near future. With the advantage of quantum computer, one can speed up not only fundamental algorithms, e.g., unstructured search [6] and factoring [11], but recent machine learning algorithms [3] as well. In this paper, we study the quantum speedup on a canonical task of reinforcement learning-best arm identification in multi-armed bandits.
We investigate the top-marm identification problem in a quantum multi-armed bandit (MAB) setting. GivenKarms whose rewards follow Bernoulli distributions with unknown means, the objective is to return themarms with the largest means with confidence at least1−δ. Many practical tasks-e.g., selecting the bestmrouting paths in a quantum network or the bestmquantum circuits for a given computation-fit naturally into this framework. We introduce Q-GapE, an elimination-based algorithm that queries each arm through a weak quantum oracle.Q- GapE attains the query complexity guaranteeO~(∑k=1K(1/Δk(m))log(1/δ)), whereΔk(m)denotes the gap between armk's mean and them-th largest mean. Compared with the best classical-oracle bound, this result offers a quadratic quantum speed-up. Extensive simulations confirm thatQ−GapEconsistently outperforms leading classical MAB algorithms in both query complexity and running time. These findings highlight the potential of quantum bandit algorithms to deliver substantial efficiency gains over their classical counterparts.
The convergence of quantum computing and robotics represents a paradigm shift in autonomous systems design, promising to overcome fundamental computational limitations that have constrained classical robotic capabilities. This comprehensive review surveys the rapidly evolving field of quantum machine learning (QML) for robotics, systematically analyzing 107 peer-reviewed contributions spanning quantum algorithms, machine learning techniques, and their robotic applications. We provide a detailed historical perspective on the field's development, from the early theoretical foundations established by Grover's search algorithm and quantum reinforcement learning proposals to current experimental implementations on noisy intermediate-scale quantum (NISQ) devices. The review systematically examines five major application domains: (1) quantum reinforcement learning for navigation and control, (2) quantum search and path planning algorithms, (3) quantum-enhanced localization and mapping, (4) quantum optimization for inverse kinematics and task allocation, and (5) multi-robot coordination and swarm intelligence. For each domain, we present detailed algorithmic formulations, computational complexity analyses, and critical assessments of experimental results. Our analysis reveals that while provable quantum advantage in robotics remains largely prospective, recent demonstrations show promising results: quantum deep reinforcement learning achieving 40\% parameter reduction in navigation tasks, Grover-based kinematic optimization demonstrating up to 93x speedups, and quantum annealing providing practical solutions for multi-robot routing. We identify key technical challenges, including barren plateaus in variational circuits, noise-induced performance degradation, and the quantum-classical integration bottleneck. Finally, we outline a strategic roadmap for quantum robotics research, distinguishing near-term opportunities in hybrid algorithms from long-term goals requiring fault-tolerant quantum computation. This paper serves as both an authoritative technical reference and a comprehensive guide for researchers working at the intersection of quantum computing and autonomous systems.
We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB), where the learner queries each arm or action through a quantum reward oracle or its inverse. Prior work gives algorithms over horizon T with regret O(KlogT) for QMAB with K arms and O(d2polylogT) for d-dimensional QLB. This leaves open the optimal dependence on K and T and whether the dependence on d can be further improved. In this work, we prove the first tight minimax regret bound of Θ(Klog(1+T/K)) for QMAB and the first lower bound of Ω(dlog(1+T/d)) for finite-action QLB, ruling out regret independent of T. Our lower bounds rely on a high-confidence single-arm quantum testing lower bound for distinguishing a fixed reward mean from an interval of alternatives. A bandit-to-testing reduction then lifts it to the QMAB lower bound, while a linear embedding gives the finite-action QLB lower bound. The matching QMAB upper bound is obtained using a tail bound for the Quantum Monte Carlo (QMC) estimator. For finite-action QLB, we propose a phased elimination algorithm that combines a low-bias low-variance quantum mean estimator with a small-support G-optimal design through a query allocation matched to the design weights. When the action set has size poly(d), its regret is nearly linear in d and matches our lower bound up to polylogarithmic factors.
Quantum reinforcement learning has emerged as a framework combining quantum computation with sequential decision-making, and applications to the multi-armed bandit (MAB) problem have been reported. The graph bandit problem extends the MAB setting by introducing spatial constraints, where the accessibility of arms is restricted by graph connectivity, yet quantum approaches to this setting remain limited. In this paper, we formulate best-arm identification in graph bandits and propose a quantum algorithmic framework, termed quantum spatial best-arm identification, which is applicable to general graph structures. This framework uses quantum walks to encode superpositions over graph-constrained actions, thereby extending amplitude amplification and generalizing the quantum BAI algorithm via Szegedy’s walk framework. We focus our theoretical analysis on complete and bipartite graphs, deriving the maximal success probability of identifying the best arm and the time step at which it is achieved. Our results clarify how quantum walk-based search can be adapted to structurally constrained decision problems and provide a foundation for quantum best-arm identification in graph-structured environments.
Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning (ML) techniques to impressive results in regression, classification, data generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limits of chip fabrication alongside the increasing size of datasets is motivating a growing number of researchers to explore the possibility of harnessing the power of quantum computation to speed up classical ML algorithms. Here we review the literature in quantum ML and discuss perspectives for a mixed readership of classical ML and quantum computation experts. Particular emphasis will be placed on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Learning in the presence of noise and certain computationally hard problems in ML are identified as promising directions for the field. Practical questions, such as how to upload classical data into quantum form, will also be addressed.