Humans and the core partition: An agent-based modeling experiment

• Published in: PloS one Vol. 17; no. 9; p. e0273961
• Main Authors: Collins, Andrew J., Etemadidavan, Sheida
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 01.09.2022; Public Library of Science (PLoS)
• Subjects: Agent-based models; Analysis; Behavior; Biology and Life Sciences; Chemical partition; Complexity; Computer and Information Sciences; Decision making; Engineering and Technology; Evaluation; Experiments; Game theory; Human acts; Human behavior; Human subjects; Physical Sciences; Research and Analysis Methods; Simulation; Social Sciences; United States
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0273961

Although strategic coalition formation is traditionally modeled using cooperative game theory, behavioral game theorists have repeatedly shown that outcomes predicted by game theory are different from those generated by actual human behavior. To further explore these differences, in a cooperative game theory context, we experiment to compare the outcomes resulting from human participants’ behavior to those generated by a cooperative game theory solution mechanism called the core partition. Our experiment uses an interactive simulation of a glove game, a particular type of cooperative game, to collect the participant’s decision choices and their resultant outcomes. Two different glove games are considered, and the outputs from 62 trial games are analyzed. The experiment’s outcomes show that core coalitions, which are coalitions in a core partition, are found in about 42% of games. Though this number may seem low, a trial’s outcome is more complex than whether the human player finds a core coalition or not. Finding the core coalition depends on factors such as the other possible feasible solutions and the payoffs available from these solutions. These factors, and the complexity they generate, are discussed in the paper.