Presentation 2022-07-04
Designing Rewards in Deep Reinforcement Learning for Chick Feeding System
Masato Kijima, Katsuhide Fujita, Tsuyoshi Shimmura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Livestock is raised cage-free, and there is an urgent need to develop an appropriate livestock management system. The key to the construction of an appropriate system is the ACI technology of "understanding" livestock and the "control" of feeders. However, it's necessary to optimize the system using reinforcement learning to construct a production management system. This study aims to design and examine a reward function for deep reinforcement learning in a chick feeding system. We developed a simulator to simulate an environment with multiple chicks and feeder robots and evaluated the proposed methods using the simulator. The effectiveness of the proposed reward function was examined by comparing its accuracy in post-training tests.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) deep reinforcement learning / chick feeding system / reward function
Paper # AI2022-2
Date of Issue 2022-06-27 (AI)

Conference Information
Committee AI
Conference Date 2022/7/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yuichi Sei(Univ. of Electro-Comm.)
Vice Chair Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.)
Secretary Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.)
Assistant Kazutaka Matsuzaki(Chuo Univ.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Designing Rewards in Deep Reinforcement Learning for Chick Feeding System
Sub Title (in English)
Keyword(1) deep reinforcement learning
Keyword(2) chick feeding system
Keyword(3) reward function
1st Author's Name Masato Kijima
1st Author's Affiliation Tokyo University of Agriculture and Technology(TAT)
2nd Author's Name Katsuhide Fujita
2nd Author's Affiliation Tokyo University of Agriculture and Technology(TAT)
3rd Author's Name Tsuyoshi Shimmura
3rd Author's Affiliation Tokyo University of Agriculture and Technology(TAT)
Date 2022-07-04
Paper # AI2022-2
Volume (vol) vol.122
Number (no) AI-94
Page pp.pp.7-12(AI),
#Pages 6
Date of Issue 2022-06-27 (AI)