Decision maker based on atomic switches

Song Ju Kim, Tohru Tsuruoka, Tsuyoshi Hasegawa, Masashi Aono, Kazuya Terabe, Masakazu Aono

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    We propose a simple model for an atomic switch-based decision maker (ASDM), and show that, as long as its total number of metal atoms is conserved when coupled with suitable operations, an atomic switch system provides a sophisticated "decision-making" capability that is known to be one of the most important intellectual abilities in human beings. We considered a popular decisionmaking problem studied in the context of reinforcement learning, the multi-armed bandit problem (MAB); the problem of finding, as accurately and quickly as possible, the most profitable option from a set of options that gives stochastic rewards. These decisions are made as dictated by each volume of precipitated metal atoms, which is moved in a manner similar to the fluctuations of a rigid body in a tug-of-war game. The "tug-of-war (TOW) dynamics" of the ASDM exhibits higher efficiency than conventional reinforcement-learning algorithms. We show analytical calculations that validate the statistical reasons for the ASDM to produce such high performance, despite its simplicity. Efficient MAB solvers are useful for many practical applications, because MAB abstracts a variety of decisionmaking problems in real-world situations where an efficient trial-and-error is required. The proposed scheme will open up a new direction in physics-based analog-computing paradigms, which will include such things as "intelligent nanodevices" based on self-judgment.

    Original languageEnglish
    Pages (from-to)245-259
    Number of pages15
    JournalAIMS Materials Science
    Volume3
    Issue number1
    DOIs
    Publication statusPublished - 2016 Jan 1

    Fingerprint

    Switches
    Reinforcement learning
    Metals
    Atoms
    Learning algorithms
    Physics
    Decision making

    Keywords

    • Amoeba-inspired computing
    • Atomic switch
    • Multi-armed bandit problem
    • Natural computing
    • Reinforcement learning
    • Tug-of-war dynamics

    ASJC Scopus subject areas

    • Materials Science(all)

    Cite this

    Kim, S. J., Tsuruoka, T., Hasegawa, T., Aono, M., Terabe, K., & Aono, M. (2016). Decision maker based on atomic switches. AIMS Materials Science, 3(1), 245-259. https://doi.org/10.3934/matersci.2016.1.245

    Decision maker based on atomic switches. / Kim, Song Ju; Tsuruoka, Tohru; Hasegawa, Tsuyoshi; Aono, Masashi; Terabe, Kazuya; Aono, Masakazu.

    In: AIMS Materials Science, Vol. 3, No. 1, 01.01.2016, p. 245-259.

    Research output: Contribution to journalArticle

    Kim, SJ, Tsuruoka, T, Hasegawa, T, Aono, M, Terabe, K & Aono, M 2016, 'Decision maker based on atomic switches', AIMS Materials Science, vol. 3, no. 1, pp. 245-259. https://doi.org/10.3934/matersci.2016.1.245
    Kim, Song Ju ; Tsuruoka, Tohru ; Hasegawa, Tsuyoshi ; Aono, Masashi ; Terabe, Kazuya ; Aono, Masakazu. / Decision maker based on atomic switches. In: AIMS Materials Science. 2016 ; Vol. 3, No. 1. pp. 245-259.
    @article{21be8a359325407c8b0fe9a069b42d75,
    title = "Decision maker based on atomic switches",
    abstract = "We propose a simple model for an atomic switch-based decision maker (ASDM), and show that, as long as its total number of metal atoms is conserved when coupled with suitable operations, an atomic switch system provides a sophisticated {"}decision-making{"} capability that is known to be one of the most important intellectual abilities in human beings. We considered a popular decisionmaking problem studied in the context of reinforcement learning, the multi-armed bandit problem (MAB); the problem of finding, as accurately and quickly as possible, the most profitable option from a set of options that gives stochastic rewards. These decisions are made as dictated by each volume of precipitated metal atoms, which is moved in a manner similar to the fluctuations of a rigid body in a tug-of-war game. The {"}tug-of-war (TOW) dynamics{"} of the ASDM exhibits higher efficiency than conventional reinforcement-learning algorithms. We show analytical calculations that validate the statistical reasons for the ASDM to produce such high performance, despite its simplicity. Efficient MAB solvers are useful for many practical applications, because MAB abstracts a variety of decisionmaking problems in real-world situations where an efficient trial-and-error is required. The proposed scheme will open up a new direction in physics-based analog-computing paradigms, which will include such things as {"}intelligent nanodevices{"} based on self-judgment.",
    keywords = "Amoeba-inspired computing, Atomic switch, Multi-armed bandit problem, Natural computing, Reinforcement learning, Tug-of-war dynamics",
    author = "Kim, {Song Ju} and Tohru Tsuruoka and Tsuyoshi Hasegawa and Masashi Aono and Kazuya Terabe and Masakazu Aono",
    year = "2016",
    month = "1",
    day = "1",
    doi = "10.3934/matersci.2016.1.245",
    language = "English",
    volume = "3",
    pages = "245--259",
    journal = "AIMS Materials Science",
    issn = "2372-0484",
    publisher = "AIMS Press",
    number = "1",

    }

    TY - JOUR

    T1 - Decision maker based on atomic switches

    AU - Kim, Song Ju

    AU - Tsuruoka, Tohru

    AU - Hasegawa, Tsuyoshi

    AU - Aono, Masashi

    AU - Terabe, Kazuya

    AU - Aono, Masakazu

    PY - 2016/1/1

    Y1 - 2016/1/1

    N2 - We propose a simple model for an atomic switch-based decision maker (ASDM), and show that, as long as its total number of metal atoms is conserved when coupled with suitable operations, an atomic switch system provides a sophisticated "decision-making" capability that is known to be one of the most important intellectual abilities in human beings. We considered a popular decisionmaking problem studied in the context of reinforcement learning, the multi-armed bandit problem (MAB); the problem of finding, as accurately and quickly as possible, the most profitable option from a set of options that gives stochastic rewards. These decisions are made as dictated by each volume of precipitated metal atoms, which is moved in a manner similar to the fluctuations of a rigid body in a tug-of-war game. The "tug-of-war (TOW) dynamics" of the ASDM exhibits higher efficiency than conventional reinforcement-learning algorithms. We show analytical calculations that validate the statistical reasons for the ASDM to produce such high performance, despite its simplicity. Efficient MAB solvers are useful for many practical applications, because MAB abstracts a variety of decisionmaking problems in real-world situations where an efficient trial-and-error is required. The proposed scheme will open up a new direction in physics-based analog-computing paradigms, which will include such things as "intelligent nanodevices" based on self-judgment.

    AB - We propose a simple model for an atomic switch-based decision maker (ASDM), and show that, as long as its total number of metal atoms is conserved when coupled with suitable operations, an atomic switch system provides a sophisticated "decision-making" capability that is known to be one of the most important intellectual abilities in human beings. We considered a popular decisionmaking problem studied in the context of reinforcement learning, the multi-armed bandit problem (MAB); the problem of finding, as accurately and quickly as possible, the most profitable option from a set of options that gives stochastic rewards. These decisions are made as dictated by each volume of precipitated metal atoms, which is moved in a manner similar to the fluctuations of a rigid body in a tug-of-war game. The "tug-of-war (TOW) dynamics" of the ASDM exhibits higher efficiency than conventional reinforcement-learning algorithms. We show analytical calculations that validate the statistical reasons for the ASDM to produce such high performance, despite its simplicity. Efficient MAB solvers are useful for many practical applications, because MAB abstracts a variety of decisionmaking problems in real-world situations where an efficient trial-and-error is required. The proposed scheme will open up a new direction in physics-based analog-computing paradigms, which will include such things as "intelligent nanodevices" based on self-judgment.

    KW - Amoeba-inspired computing

    KW - Atomic switch

    KW - Multi-armed bandit problem

    KW - Natural computing

    KW - Reinforcement learning

    KW - Tug-of-war dynamics

    UR - http://www.scopus.com/inward/record.url?scp=84979584926&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84979584926&partnerID=8YFLogxK

    U2 - 10.3934/matersci.2016.1.245

    DO - 10.3934/matersci.2016.1.245

    M3 - Article

    VL - 3

    SP - 245

    EP - 259

    JO - AIMS Materials Science

    JF - AIMS Materials Science

    SN - 2372-0484

    IS - 1

    ER -