To be Big Picture Thinker or Detail-Oriented?: Utilizing Perceived Gist Information to Achieve Efficient Convention Emergence with Bilateralism and Multilateralism
Refereed conference paper presented and published in conference proceedings


Full Text

Other information
AbstractRecently, the study of social conventions (or norms) has attracted much attention. In this paper, we study the emergence of conventions from agents' repeated coordination games via bilateralism and multilateralism. We assume that agents can perceive the gist information, i.e., a big picture of how popular each action is in their neighbourhood. A novel reinforcement learning approach which utilizes the gist information is proposed. Experiment verifies that the proposed approach significantly outperforms the baseline and the state-of-the-art approaches, in terms of the speed of convention emergence.
All Author(s) ListShuyue Hu, Chin-wing Leung, Ho-fung Leung, Jiamou Liu
Name of Conference18th International Conference on Autonomous Agents and MultiAgent Systems
Start Date of Conference13/05/2019
End Date of Conference17/05/2019
Place of ConferenceMontreal QC
Country/Region of ConferenceCanada
Proceedings TitleAAMAS '19 Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems
Year2019
Pages2021 - 2023
ISBN978-1-4503-6309-9
LanguagesEnglish-United States

Last updated on 2019-20-12 at 16:52