EUVIMEDEUVIMED entdecken
Crossref

Learning Roles With Emergent Social Value Orientations

Wenhao Li, Xiangfeng Wang, Bo Jin, Jingyi Lu, Hongyuan Zha

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 1657-1673

DOI: 10.1109/tpami.2025.3620954 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Wenhao Li und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Social Values, Game Theory, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 106 Literaturangaben. Gefördert von: National Natural Science Foundation of China, STCSM Shanghai Rising-Star Program, Science, Technology and Innovation Commission of Shenzhen Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Social dilemmas can be considered situations where individual rationality leads to collective irrationality. The multi-agent reinforcement learning community has leveraged ideas from social science, such as social value orientations (SVO), to solve social dilemmas in complex cooperative tasks. In this paper, we first introduce the typical "division of labor or roles" mechanism in human society, and provide a promising solution for intertemporal social dilemmas (ISD) with SVOs. A novel learning framework, called Learning Roles with Emergent SVOs (RESVO), is proposed to transform the learning of roles into the social value orientation emergence, which is symmetrically solved by endowing agents with altruism to share rewards with other agents. An SVO-based role embedding space is then constructed by individual conditioning policies on roles with a novel rank regularizer and mutual information maximizer. Experiments show that RESVO achieves a stable division of labor and cooperation in ISDs with different complexity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Social ValuesGame TheoryMachine LearningHumansCooperative BehaviorAlgorithms

Förderung

  • National Natural Science Foundation of China
  • STCSM Shanghai Rising-Star Program
  • Science, Technology and Innovation Commission of Shenzhen Municipality

Zitieren

APA

Li, W., Wang, X., Jin, B., Lu, J., & Zha, H. (2026). Learning Roles With Emergent Social Value Orientations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 1657-1673. https://doi.org/10.1109/tpami.2025.3620954

Vancouver

Li W, Wang X, Jin B, Lu J, Zha H. Learning Roles With Emergent Social Value Orientations. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):1657-1673. doi:10.1109/tpami.2025.3620954

BibTeX
@article{Li2026,
  author = {Li, Wenhao and Wang, Xiangfeng and Jin, Bo and Lu, Jingyi and Zha, Hongyuan},
  title = {Learning Roles With Emergent Social Value Orientations},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {1657--1673},
  doi = {10.1109/tpami.2025.3620954}
}
Kostenlos starten →