Quantum Exploration Algorithms for Multi-Armed Bandits

被引：0
|
作者：
Wang, Daochen [1 ,2 ]
You, Xuchen [1 ,3 ,4 ]
Li, Tongyang [1 ,3 ,4 ,5 ]
Childs, Andrew M. [1 ,3 ,4 ]
机构：
[1] Univ Maryland, Joint Ctr Quantum Informat & Comp Sci, College Pk, MD 20742 USA
[2] Univ Maryland, Dept Math, College Pk, MD 20742 USA
[3] Univ Maryland, Dept Comp Sci, College Pk, MD 20742 USA
[4] Univ Maryland, Inst Adv Comp Studies, College Pk, MD 20742 USA
[5] MIT, Ctr Theoret Phys, Cambridge, MA 02139 USA
来源：
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2021年 / 35卷
基金：
美国国家科学基金会;
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Identifying the best arm of a multi-armed bandit is a central problem in bandit optimization. We study a quantum computational version of this problem with coherent oracle access to states encoding the reward probabilities of each arm as quantum amplitudes. Specifically, we provide an algorithm to find the best arm with fixed confidence based on variable-time amplitude amplification and estimation. This algorithm gives a quadratic speedup compared to the best possible classical result in terms of query complexity. We also prove a matching quantum lower bound (up to poly-logarithmic factors).
引用
收藏
页码：10102 / 10110
页数：9
相关论文
共 50 条
  • [31] Exploration with Limited Memory: Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-armed Bandits
    Assadi, Sepehr
    Wang, Chen
    PROCEEDINGS OF THE 52ND ANNUAL ACM SIGACT SYMPOSIUM ON THEORY OF COMPUTING (STOC '20), 2020, : 1237 - 1250
  • [32] Designing multi-objective multi-armed bandits algorithms: a study
    Drugan, Madalina M.
    Nowe, Ann
    2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
  • [33] Optimal Algorithms for Range Searching over Multi-Armed Bandits
    Barman, Siddharth
    Krishnamurthy, Ramakrishnan
    Rahul, Saladi
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 2177 - 2183
  • [34] Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets
    Wan, Zongqi
    Zhang, Zhijie
    Li, Tongyang
    Zhang, Jialin
    Sun, Xiaoming
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 8, 2023, : 10087 - 10094
  • [35] Coordinated Versus Decentralized Exploration In Multi-Agent Multi-Armed Bandits
    Chakraborty, Mithun
    Chua, Kai Yee Phoebe
    Das, Sanmay
    Juba, Brendan
    PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 164 - 170
  • [36] Fast Beam Alignment via Pure Exploration in Multi-Armed Bandits
    Wei, Yi
    Zhong, Zixin
    Tan, Vincent Y. F.
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (05) : 3264 - 3279
  • [37] Pure Exploration of Multi-Armed Bandits with Heavy-Tailed Payoffs
    Yu, Xiaotian
    Shao, Han
    Lyu, Michael R.
    King, Irwin
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2018, : 937 - 946
  • [38] Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits
    Benureau, Fabien
    Oudeyer, Pierre-Yves
    5TH INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING AND ON EPIGENETIC ROBOTICS (ICDL-EPIROB), 2015, : 135 - 142
  • [39] Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits
    Rouyer, Chloe
    Seldin, Yevgeny
    CONFERENCE ON LEARNING THEORY, VOL 125, 2020, 125
  • [40] Aggregation of Multi-Armed Bandits Learning Algorithms for Opportunistic Spectrum Access
    Besson, Lilian
    Kaufmann, Emilie
    Moy, Christophe
    2018 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2018,
12345