Emergent Resource Exchange and Tolerated Theft Behavior Using Multiagent Reinforcement Learning
Artificial Life · 2024
DOI: 10.1162/artl_a_00423 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Life, 2024. Verfasst von Jack Garbus und 1 weiteren Autor:innen. Beteiligte Einrichtung: Brandeis University, Department of Computer Science. garbus@brandeis.edu. Hauptthemen laut MEDLINE: Cooperative Behavior, Theft. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
For decades, the evolution of cooperation has piqued interest in numerous academic disciplines, such as game theory, economics, biology, and computer science. In this work, we demonstrate the emergence of a novel and effective resource exchange protocol formed by dropping and picking up resources in a foraging environment. This form of cooperation is made possible by the introduction of a campfire, which adds an extended period of congregation and downtime for agents to explore otherwise unlikely interactions. We find that the agents learn to avoid getting cheated by their exchange partners, but not always from a third party. We also observe the emergence of behavior analogous to tolerated theft, despite the lack of any punishment, combat, or larceny mechanism in the environment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Brandeis University, Department of Computer Science. garbus@brandeis.edu.
- Brandeis University, Department of Computer Science.
Zitieren
APA
Garbus, J., & Pollack, J. (2024). Emergent Resource Exchange and Tolerated Theft Behavior Using Multiagent Reinforcement Learning. Artificial Life. https://doi.org/10.1162/artl_a_00423
Vancouver
Garbus J, Pollack J. Emergent Resource Exchange and Tolerated Theft Behavior Using Multiagent Reinforcement Learning. Artificial Life. 2024. doi:10.1162/artl_a_00423
BibTeX
@article{Garbus2024,
author = {Garbus, Jack and Pollack, Jordan},
title = {Emergent Resource Exchange and Tolerated Theft Behavior Using Multiagent Reinforcement Learning},
journal = {Artificial Life},
year = {2024},
doi = {10.1162/artl_a_00423}
}
EUVIMED