Saved in:
Bibliographic Details
Main Authors: Gelpí, Rebekah A., Ju, Yibing, Jackson, Ethan C., Tang, Yikai, Verch, Shon, Voelcker, Claas, Cunningham, William A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.00228
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916770386804736
author Gelpí, Rebekah A.
Ju, Yibing
Jackson, Ethan C.
Tang, Yikai
Verch, Shon
Voelcker, Claas
Cunningham, William A.
author_facet Gelpí, Rebekah A.
Ju, Yibing
Jackson, Ethan C.
Tang, Yikai
Verch, Shon
Voelcker, Claas
Cunningham, William A.
contents We introduce Sorrel (https://github.com/social-ai-uoft/sorrel), a simple Python interface for generating and testing new multi-agent reinforcement learning environments. This interface places a high degree of emphasis on simplicity and accessibility, and uses a more psychologically intuitive structure for the basic agent-environment loop, making it a useful tool for social scientists to investigate how learning and social interaction leads to the development and change of group dynamics. In this short paper, we outline the basic design philosophy and features of Sorrel.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00228
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sorrel: A simple and flexible framework for multi-agent reinforcement learning
Gelpí, Rebekah A.
Ju, Yibing
Jackson, Ethan C.
Tang, Yikai
Verch, Shon
Voelcker, Claas
Cunningham, William A.
Multiagent Systems
Machine Learning
We introduce Sorrel (https://github.com/social-ai-uoft/sorrel), a simple Python interface for generating and testing new multi-agent reinforcement learning environments. This interface places a high degree of emphasis on simplicity and accessibility, and uses a more psychologically intuitive structure for the basic agent-environment loop, making it a useful tool for social scientists to investigate how learning and social interaction leads to the development and change of group dynamics. In this short paper, we outline the basic design philosophy and features of Sorrel.
title Sorrel: A simple and flexible framework for multi-agent reinforcement learning
topic Multiagent Systems
Machine Learning
url https://arxiv.org/abs/2506.00228