Presentation | 2023-03-03 Study on the resilient role in coordinated behavior of a triad using deep reinforcement learning and rule-based modeling Jun Ichikawa, Kazushi Tsutsui, Keisuke Fujii, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Group can often implement a task, which is difficult to do alone, or achieve higher performance than an individual. For such coordination, adjustments based on two types of information processing are crucial; (1) bottom-up of obtaining and using other members' states through haptic and visual senses and (2) top-down based on a group goal, task limitations, and a role. However, coordinated group behavior is not fully investigated from both processing. Meanwhile, our previous study conducted the behavioral experiment; triads repeatedly engaged in a coordinated drawing task where participants changed tensions by reels, shared heterogeneous roles, and moved a pen connected to the three threads to draw an equilateral triangle. The results suggested that a resilient role, which adjusted to help others and improve situations, was related to performance. In such a role, the above-mentioned processing would work; this study investigated the resilient role in the task using deep reinforcement learning and rule-based modeling. The simulation results indicated that the condition, in which an agent in this role acted by bottom-up and top-down processing, achieved higher performance (smaller pen deviation) than the only rule-based and random conditions. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | coordinated group behavior / role sharing / resilience / deep reinforcement learning / rule-based modeling |
Paper # | HCS2022-93 |
Date of Issue | 2023-02-23 (HCS) |
Conference Information | |
Committee | HCS |
---|---|
Conference Date | 2023/3/2(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tokoha University(KusanagiCampus) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Interaction modeling, etc. |
Chair | Tomoko Kanda(Osaka Inst. of Tech.) |
Vice Chair | Yugo Hayashi(Ritsumeikan Univ.) / Masashi Komori(Osaka Electro-Comm. Univ.) |
Secretary | Yugo Hayashi(Nihon Univ.) / Masashi Komori(Kanagawa Univ.) |
Assistant | HUANG HUNGHSUAN(Univ. of Fukuchiyama) / Jun Ichikawa(Shizuoka Univ.) / Kazuki Takashima(Tohoku Univ.) / Hiroto Saito(Tokyo Denki Univ.) / Ryo Ishii(NTT) / Yoshimasa Ohmoto(Shizuoka Univ.) |
Paper Information | |
Registration To | Technical Committee on Human Communication Science |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Study on the resilient role in coordinated behavior of a triad using deep reinforcement learning and rule-based modeling |
Sub Title (in English) | |
Keyword(1) | coordinated group behavior |
Keyword(2) | role sharing |
Keyword(3) | resilience |
Keyword(4) | deep reinforcement learning |
Keyword(5) | rule-based modeling |
1st Author's Name | Jun Ichikawa |
1st Author's Affiliation | Shizuoka University(Shizuoka Univ.) |
2nd Author's Name | Kazushi Tsutsui |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
3rd Author's Name | Keisuke Fujii |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2023-03-03 |
Paper # | HCS2022-93 |
Volume (vol) | vol.122 |
Number (no) | HCS-413 |
Page | pp.pp.100-105(HCS), |
#Pages | 6 |
Date of Issue | 2023-02-23 (HCS) |