Data-driven vs model-driven imitative learning

Tembine Hamidou

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    One of the fundamental problems of an interconnected interactive system is the huge amounts of data that are being generated by every entity. Unfortunately, what we seek is not data but information, and therefore, a growing bottleneck is exactly how to extract and learn useful information from data. In this paper, the information-Theoretic learning in data-driven games is studied. This learning shows that the imitative Boltzmann-Gibbs strategy is the maximizer of the perturbed payoff where the perturbation function is the relative entropy from the previous strategy to the current one. In particular, the imitative strategy is the best learning scheme with the respect to data-driven games with cost of moves. Based on it, the classical imitative Boltzmann-Gibbs learning in data-driven games is revisited. Due to communication complexity and noisy data measurements, the classical imitative Boltzmann-Gibbs cannot be applied directly in situations were only numerical values of player's own payoff is measured. A combined fully distributed payoff and strategy imitative learning (CODIPAS) is proposed. Connections between the rest points of the resulting game dynamics, equilibria are established.

    Original languageEnglish (US)
    Title of host publicationProceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages22-29
    Number of pages8
    ISBN (Electronic)9781509054619
    DOIs
    StatePublished - Oct 13 2017
    Event6th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2017 - Chongqing, China
    Duration: May 26 2017May 27 2017

    Other

    Other6th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2017
    CountryChina
    CityChongqing
    Period5/26/175/27/17

    Fingerprint

    Entropy
    Communication
    Costs

    Keywords

    • Data-driven Learning
    • Distributed Systems
    • Game Dynamics
    • Imitation
    • Noisy Games

    ASJC Scopus subject areas

    • Computational Mechanics
    • Artificial Intelligence
    • Computer Networks and Communications

    Cite this

    Hamidou, T. (2017). Data-driven vs model-driven imitative learning. In Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017 (pp. 22-29). [8067719] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DDCLS.2017.8067719

    Data-driven vs model-driven imitative learning. / Hamidou, Tembine.

    Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 22-29 8067719.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Hamidou, T 2017, Data-driven vs model-driven imitative learning. in Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017., 8067719, Institute of Electrical and Electronics Engineers Inc., pp. 22-29, 6th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2017, Chongqing, China, 5/26/17. https://doi.org/10.1109/DDCLS.2017.8067719
    Hamidou T. Data-driven vs model-driven imitative learning. In Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 22-29. 8067719 https://doi.org/10.1109/DDCLS.2017.8067719
    Hamidou, Tembine. / Data-driven vs model-driven imitative learning. Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 22-29
    @inproceedings{e69a6053a73949d3a2dd641499319fc9,
    title = "Data-driven vs model-driven imitative learning",
    abstract = "One of the fundamental problems of an interconnected interactive system is the huge amounts of data that are being generated by every entity. Unfortunately, what we seek is not data but information, and therefore, a growing bottleneck is exactly how to extract and learn useful information from data. In this paper, the information-Theoretic learning in data-driven games is studied. This learning shows that the imitative Boltzmann-Gibbs strategy is the maximizer of the perturbed payoff where the perturbation function is the relative entropy from the previous strategy to the current one. In particular, the imitative strategy is the best learning scheme with the respect to data-driven games with cost of moves. Based on it, the classical imitative Boltzmann-Gibbs learning in data-driven games is revisited. Due to communication complexity and noisy data measurements, the classical imitative Boltzmann-Gibbs cannot be applied directly in situations were only numerical values of player's own payoff is measured. A combined fully distributed payoff and strategy imitative learning (CODIPAS) is proposed. Connections between the rest points of the resulting game dynamics, equilibria are established.",
    keywords = "Data-driven Learning, Distributed Systems, Game Dynamics, Imitation, Noisy Games",
    author = "Tembine Hamidou",
    year = "2017",
    month = "10",
    day = "13",
    doi = "10.1109/DDCLS.2017.8067719",
    language = "English (US)",
    pages = "22--29",
    booktitle = "Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Data-driven vs model-driven imitative learning

    AU - Hamidou, Tembine

    PY - 2017/10/13

    Y1 - 2017/10/13

    N2 - One of the fundamental problems of an interconnected interactive system is the huge amounts of data that are being generated by every entity. Unfortunately, what we seek is not data but information, and therefore, a growing bottleneck is exactly how to extract and learn useful information from data. In this paper, the information-Theoretic learning in data-driven games is studied. This learning shows that the imitative Boltzmann-Gibbs strategy is the maximizer of the perturbed payoff where the perturbation function is the relative entropy from the previous strategy to the current one. In particular, the imitative strategy is the best learning scheme with the respect to data-driven games with cost of moves. Based on it, the classical imitative Boltzmann-Gibbs learning in data-driven games is revisited. Due to communication complexity and noisy data measurements, the classical imitative Boltzmann-Gibbs cannot be applied directly in situations were only numerical values of player's own payoff is measured. A combined fully distributed payoff and strategy imitative learning (CODIPAS) is proposed. Connections between the rest points of the resulting game dynamics, equilibria are established.

    AB - One of the fundamental problems of an interconnected interactive system is the huge amounts of data that are being generated by every entity. Unfortunately, what we seek is not data but information, and therefore, a growing bottleneck is exactly how to extract and learn useful information from data. In this paper, the information-Theoretic learning in data-driven games is studied. This learning shows that the imitative Boltzmann-Gibbs strategy is the maximizer of the perturbed payoff where the perturbation function is the relative entropy from the previous strategy to the current one. In particular, the imitative strategy is the best learning scheme with the respect to data-driven games with cost of moves. Based on it, the classical imitative Boltzmann-Gibbs learning in data-driven games is revisited. Due to communication complexity and noisy data measurements, the classical imitative Boltzmann-Gibbs cannot be applied directly in situations were only numerical values of player's own payoff is measured. A combined fully distributed payoff and strategy imitative learning (CODIPAS) is proposed. Connections between the rest points of the resulting game dynamics, equilibria are established.

    KW - Data-driven Learning

    KW - Distributed Systems

    KW - Game Dynamics

    KW - Imitation

    KW - Noisy Games

    UR - http://www.scopus.com/inward/record.url?scp=85034033934&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85034033934&partnerID=8YFLogxK

    U2 - 10.1109/DDCLS.2017.8067719

    DO - 10.1109/DDCLS.2017.8067719

    M3 - Conference contribution

    SP - 22

    EP - 29

    BT - Proceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -