Adaptive Task Allocation Based on Social Utility and Individual Preference in Distributed Environments

Naoki Iijima, Ayumi Sugiyama, Masashi Hayano, Toshiharu Sugawara

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    Recent advances in computer and network technologies enable the provision of many services combining multiple types of information and different computational capabilities. The tasks for these services are executed by allocating them to appropriate collaborative agents, which are computational entities with specific functionality. However, the number of these tasks is huge, and these tasks appear simultaneously, and appropriate allocation strongly depends on the agent's capability and the resource patterns required to complete tasks. Thus, we first propose a task allocation method in which, although the social utility for the shared and required performance is attempted to be maximized, agents also give weight to individual preferences based on their own specifications and capabilities. We also propose a learning method in which collaborative agents autonomously decide the preference adaptively in the dynamic environment. We experimentally demonstrate that the appropriate strategy to decide the preference depends on the type of task and the features of the task reward. We then show that agents using the proposed learning method adaptively decided their preference and could maintain excellent performance in a changing environment.

    Original languageEnglish
    Pages (from-to)91-98
    Number of pages8
    JournalProcedia Computer Science
    Volume112
    DOIs
    Publication statusPublished - 2017

    Fingerprint

    Specifications

    Keywords

    • Cooperative agent
    • Preference
    • Reinforcement learning
    • Task allocation

    ASJC Scopus subject areas

    • Computer Science(all)

    Cite this

    Adaptive Task Allocation Based on Social Utility and Individual Preference in Distributed Environments. / Iijima, Naoki; Sugiyama, Ayumi; Hayano, Masashi; Sugawara, Toshiharu.

    In: Procedia Computer Science, Vol. 112, 2017, p. 91-98.

    Research output: Contribution to journalArticle

    @article{7e6af25dc8e14c1894fd68984807f302,
    title = "Adaptive Task Allocation Based on Social Utility and Individual Preference in Distributed Environments",
    abstract = "Recent advances in computer and network technologies enable the provision of many services combining multiple types of information and different computational capabilities. The tasks for these services are executed by allocating them to appropriate collaborative agents, which are computational entities with specific functionality. However, the number of these tasks is huge, and these tasks appear simultaneously, and appropriate allocation strongly depends on the agent's capability and the resource patterns required to complete tasks. Thus, we first propose a task allocation method in which, although the social utility for the shared and required performance is attempted to be maximized, agents also give weight to individual preferences based on their own specifications and capabilities. We also propose a learning method in which collaborative agents autonomously decide the preference adaptively in the dynamic environment. We experimentally demonstrate that the appropriate strategy to decide the preference depends on the type of task and the features of the task reward. We then show that agents using the proposed learning method adaptively decided their preference and could maintain excellent performance in a changing environment.",
    keywords = "Cooperative agent, Preference, Reinforcement learning, Task allocation",
    author = "Naoki Iijima and Ayumi Sugiyama and Masashi Hayano and Toshiharu Sugawara",
    year = "2017",
    doi = "10.1016/j.procs.2017.08.177",
    language = "English",
    volume = "112",
    pages = "91--98",
    journal = "Procedia Computer Science",
    issn = "1877-0509",
    publisher = "Elsevier BV",

    }

    TY - JOUR

    T1 - Adaptive Task Allocation Based on Social Utility and Individual Preference in Distributed Environments

    AU - Iijima, Naoki

    AU - Sugiyama, Ayumi

    AU - Hayano, Masashi

    AU - Sugawara, Toshiharu

    PY - 2017

    Y1 - 2017

    N2 - Recent advances in computer and network technologies enable the provision of many services combining multiple types of information and different computational capabilities. The tasks for these services are executed by allocating them to appropriate collaborative agents, which are computational entities with specific functionality. However, the number of these tasks is huge, and these tasks appear simultaneously, and appropriate allocation strongly depends on the agent's capability and the resource patterns required to complete tasks. Thus, we first propose a task allocation method in which, although the social utility for the shared and required performance is attempted to be maximized, agents also give weight to individual preferences based on their own specifications and capabilities. We also propose a learning method in which collaborative agents autonomously decide the preference adaptively in the dynamic environment. We experimentally demonstrate that the appropriate strategy to decide the preference depends on the type of task and the features of the task reward. We then show that agents using the proposed learning method adaptively decided their preference and could maintain excellent performance in a changing environment.

    AB - Recent advances in computer and network technologies enable the provision of many services combining multiple types of information and different computational capabilities. The tasks for these services are executed by allocating them to appropriate collaborative agents, which are computational entities with specific functionality. However, the number of these tasks is huge, and these tasks appear simultaneously, and appropriate allocation strongly depends on the agent's capability and the resource patterns required to complete tasks. Thus, we first propose a task allocation method in which, although the social utility for the shared and required performance is attempted to be maximized, agents also give weight to individual preferences based on their own specifications and capabilities. We also propose a learning method in which collaborative agents autonomously decide the preference adaptively in the dynamic environment. We experimentally demonstrate that the appropriate strategy to decide the preference depends on the type of task and the features of the task reward. We then show that agents using the proposed learning method adaptively decided their preference and could maintain excellent performance in a changing environment.

    KW - Cooperative agent

    KW - Preference

    KW - Reinforcement learning

    KW - Task allocation

    UR - http://www.scopus.com/inward/record.url?scp=85032363036&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85032363036&partnerID=8YFLogxK

    U2 - 10.1016/j.procs.2017.08.177

    DO - 10.1016/j.procs.2017.08.177

    M3 - Article

    VL - 112

    SP - 91

    EP - 98

    JO - Procedia Computer Science

    JF - Procedia Computer Science

    SN - 1877-0509

    ER -