Main content

Home

Menu

View
Wiki Version:
Incentivising Cooperation by Judging a Group's Performance by its Weakest Member in Neuroevolution and Reinforcement Learning Description: This project explores how cooperation among autonomous agents can be incentivized by rewarding group performance based on the weakest member. We compare various reward schemes (MEAN, MAXIMUM, MINIMUM) in both neuroevolution (via genetic algorithms) and reinforcement learning contexts. Results demonstrate that the MINIMUM reward scheme promotes both high performance and equitable behavior, flattening the despotic index. The uploaded ZIP file contains all source code, data, figures, and generated results necessary to reproduce the experiments and analyses presented in the paper. The implementation of the evolutionary framework, MABE (Modular Agent-Based Evolver), can be found on GitHub at: https://github.com/Hintzelab/MABE
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
Accept
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.
Accept
×

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.

Copyright © 2011-2025 Center for Open Science | Terms of Use | Privacy Policy | Status | API
TOP Guidelines | Reproducibility Project: Psychology | Reproducibility Project: Cancer Biology