Sorrel: A simple and flexible framework for multi-agent reinforcement learning
Rebekah A. Gelpí, Yibing Ju, Ethan C. Jackson, Yikai Tang, Shon Verch, Claas Voelcker, William A. Cunningham
Abstract
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.
Related Papers
One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms2025-07-21Streaming 4D Visual Geometry Transformer2025-07-15A Learning Framework For Cooperative Collision Avoidance of UAV Swarms Leveraging Domain Knowledge2025-07-15Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning2025-07-09AI-Reporter: A Path to a New Genre of Scientific Communication2025-07-08SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning2025-06-30The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind2025-06-25Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning2025-06-24