EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning

Naoto Yoshida iD, Etsushi Arikawa, Hoshinori Kanazawa iD, Yasuo Kuniyoshi iD

PNAS Nexus · 28.11.2024 · 3 (12)

DOI: 10.1093/pnasnexus/pgae540 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PNAS Nexus, online erschienen am 28.11.2024. Verfasst von Naoto Yoshida und 3 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Information Science and Technology, The University of Tokyo, Tokyo 113-8656, Japan. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS, KAKENHI, AMED.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The continual generation of behaviors that satisfy all conflicting demands that cannot be satisfied simultaneously, is a situation that is seen naturally in autonomous agents such as long-term operating household robots, and in animals in the natural world. Homeostatic reinforcement learning (homeostatic RL) is known as a bio-inspired framework that achieves such multiobjective control through behavioral optimization. Homeostatic RL achieves autonomous behavior optimization using only internal body information in complex environmental systems, including continuous motor control. However, it is still unknown whether the resulting behaviors actually have the similar long-term properties as real animals. To clarify this issue, this study focuses on the balancing of multiple nutrients in animal foraging as a situation in which such multiobjective control is achieved in animals in the natural world. We then focus on the nutritional geometry framework, which can quantitatively handle the long-term characteristics of foraging strategies for multiple nutrients in nutritional biology, and construct a similar verification environment to show experimentally that homeostatic RL agents exhibit long-term foraging characteristics seen in animals in nature. Furthermore, numerical simulation results show that the long-term foraging characteristics of the agent can be controlled by changing the weighting for the agent’s multiobjective motivation. These results show that the long-term behavioral characteristics of homeostatic RL agents that perform behavioral emergence at the motor control level can be predicted and designed based on the internal dynamics of the body and the weighting of motivation, which change in real time.

Schlagwörter

Stichwörter der Autor:innen

deep reinforcement learninghomeostasisnutritionnutritional geometry framework

Autor:innen und Institutionen

  • Graduate School of Information Science and Technology, The University of Tokyo, Tokyo 113-8656, Japan.
  • Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan.
  • Next Generation Artificial Intelligence Research Center, The University of Tokyo, Tokyo 113-8656, Japan.

ORCID-Profile: Naoto Yoshida, Hoshinori Kanazawa, Yasuo Kuniyoshi

Förderung

  • JSPS
  • KAKENHI
  • AMED

Zitieren

APA

Yoshida, N., Arikawa, E., Kanazawa, H., & Kuniyoshi, Y. (2024). Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning. PNAS Nexus, 3(12). https://doi.org/10.1093/pnasnexus/pgae540

Vancouver

Yoshida N, Arikawa E, Kanazawa H, Kuniyoshi Y. Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning. PNAS Nexus. 2024;3(12). doi:10.1093/pnasnexus/pgae540

BibTeX
@article{Yoshida2024,
  author = {Yoshida, Naoto and Arikawa, Etsushi and Kanazawa, Hoshinori and Kuniyoshi, Yasuo},
  title = {Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning},
  journal = {PNAS Nexus},
  year = {2024},
  volume = {3},
  number = {12},
  doi = {10.1093/pnasnexus/pgae540}
}
Kostenlos starten →