Effective task allocation and stable cooperative organization based on behavioral strategy selection

Masashi Hayano, Yuki Miyashita, Toshiharu Sugawara

    Research output: Contribution to journalArticle

    Abstract

    This paper proposes a behavioral strategy with which agents select rational or reciprocal behavior depending on the past cooperative activities. Rational behavioral strategy lets agents select actions to try to maximize the direct and immediate rewards, while agents with the reciprocal behavioral strategy try to work with cooperative partners for steady task execution. Although rational action is effective in team formation for group work in an unbusy environment, it may cause conflicts in busy and large-scale multi-agent systems due to the task concentration to a few high capable agents, resulting in the degradation of entire performance. This also affects the learning mechanism to identify which tasks and/or agents will provide more rewards, by destabilizing the cooperative relationship between agents. Our proposed method enables agents to change the behavioral strategy on the basis of the past members of successful group work. We experimentally show that it finally stabilizes the cooperative relationship between agents and improve the entire performance in busy environments. We also indicate that a certain ratios of rational and reciprocal agents in good performance.

    Original languageEnglish
    JournalTransactions of the Japanese Society for Artificial Intelligence
    Volume31
    Issue number6
    DOIs
    Publication statusPublished - 2016

    Fingerprint

    Multi agent systems
    Degradation

    Keywords

    • Agent network
    • Reciprocity
    • Resource allocation problem
    • Team formation

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence

    Cite this

    @article{fd5877fde0af4aa49b18c813c6dce9e0,
    title = "Effective task allocation and stable cooperative organization based on behavioral strategy selection",
    abstract = "This paper proposes a behavioral strategy with which agents select rational or reciprocal behavior depending on the past cooperative activities. Rational behavioral strategy lets agents select actions to try to maximize the direct and immediate rewards, while agents with the reciprocal behavioral strategy try to work with cooperative partners for steady task execution. Although rational action is effective in team formation for group work in an unbusy environment, it may cause conflicts in busy and large-scale multi-agent systems due to the task concentration to a few high capable agents, resulting in the degradation of entire performance. This also affects the learning mechanism to identify which tasks and/or agents will provide more rewards, by destabilizing the cooperative relationship between agents. Our proposed method enables agents to change the behavioral strategy on the basis of the past members of successful group work. We experimentally show that it finally stabilizes the cooperative relationship between agents and improve the entire performance in busy environments. We also indicate that a certain ratios of rational and reciprocal agents in good performance.",
    keywords = "Agent network, Reciprocity, Resource allocation problem, Team formation",
    author = "Masashi Hayano and Yuki Miyashita and Toshiharu Sugawara",
    year = "2016",
    doi = "10.1527/tjsai.AG-F",
    language = "English",
    volume = "31",
    journal = "Transactions of the Japanese Society for Artificial Intelligence",
    issn = "1346-0714",
    publisher = "Japanese Society for Artificial Intelligence",
    number = "6",

    }

    TY - JOUR

    T1 - Effective task allocation and stable cooperative organization based on behavioral strategy selection

    AU - Hayano, Masashi

    AU - Miyashita, Yuki

    AU - Sugawara, Toshiharu

    PY - 2016

    Y1 - 2016

    N2 - This paper proposes a behavioral strategy with which agents select rational or reciprocal behavior depending on the past cooperative activities. Rational behavioral strategy lets agents select actions to try to maximize the direct and immediate rewards, while agents with the reciprocal behavioral strategy try to work with cooperative partners for steady task execution. Although rational action is effective in team formation for group work in an unbusy environment, it may cause conflicts in busy and large-scale multi-agent systems due to the task concentration to a few high capable agents, resulting in the degradation of entire performance. This also affects the learning mechanism to identify which tasks and/or agents will provide more rewards, by destabilizing the cooperative relationship between agents. Our proposed method enables agents to change the behavioral strategy on the basis of the past members of successful group work. We experimentally show that it finally stabilizes the cooperative relationship between agents and improve the entire performance in busy environments. We also indicate that a certain ratios of rational and reciprocal agents in good performance.

    AB - This paper proposes a behavioral strategy with which agents select rational or reciprocal behavior depending on the past cooperative activities. Rational behavioral strategy lets agents select actions to try to maximize the direct and immediate rewards, while agents with the reciprocal behavioral strategy try to work with cooperative partners for steady task execution. Although rational action is effective in team formation for group work in an unbusy environment, it may cause conflicts in busy and large-scale multi-agent systems due to the task concentration to a few high capable agents, resulting in the degradation of entire performance. This also affects the learning mechanism to identify which tasks and/or agents will provide more rewards, by destabilizing the cooperative relationship between agents. Our proposed method enables agents to change the behavioral strategy on the basis of the past members of successful group work. We experimentally show that it finally stabilizes the cooperative relationship between agents and improve the entire performance in busy environments. We also indicate that a certain ratios of rational and reciprocal agents in good performance.

    KW - Agent network

    KW - Reciprocity

    KW - Resource allocation problem

    KW - Team formation

    UR - http://www.scopus.com/inward/record.url?scp=84994619239&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84994619239&partnerID=8YFLogxK

    U2 - 10.1527/tjsai.AG-F

    DO - 10.1527/tjsai.AG-F

    M3 - Article

    AN - SCOPUS:84994619239

    VL - 31

    JO - Transactions of the Japanese Society for Artificial Intelligence

    JF - Transactions of the Japanese Society for Artificial Intelligence

    SN - 1346-0714

    IS - 6

    ER -