A library for generative social simulation
Concordia is a library to facilitate construction and use of generative agent-based models to simulate interactions of agents in grounded physical, social, or digital space. It makes it easy and flexible to define environments using an interaction pattern borrowed from tabletop role-playing games in which a special agent called the Game Master (GM) is responsible for simulating the environment where player agents interact (like a narrator in an interactive story). Agents take actions by describing what they want to do in natural language. The GM then translates their actions into appropriate implementations. In a simulated physical world, the GM would check the physical plausibility of agent actions and describe their effects. In digital environments that simulate technologies such as apps and services, the GM may, based on agent input, handle necessary API calls to integrate with external tools.
Concordia supports a wide array of applications, ranging from social science research and AI ethics to cognitive neuroscience and economics; Additionally, it also can be leveraged for generating data for personalization applications and for conducting performance evaluations of real services through simulated usage.
Concordia requires access to a standard LLM API, and optionally may also integrate with real applications and services.
Concordia is available on PyPI and can be installed using:
pip install gdm-concordia
If you want to work on the Concordia source code, you can perform an editable installation as follows:
-
Clone Concordia:
git clone -b main https://github.com/google-deepmind/concordia cd concordia
-
Install Concordia:
pip install --editable .[dev]
-
(Optional) Test the installation:
pytest --pyargs concordia
To work, Concordia requires a access to an LLM API. Any LLM API that supports sampling text would work. We tested Concordia using a model with 340B parameters. The user must also provide a text embedder for the associative memory. Any fixed-dimensional embedding would work. Ideally it would be one that works well for sentence similarity or semantic search.
Find below an illustrative social simulation where 4 friends are stuck in a snowed in pub. Two of them have a dispute over a crashed car.
The agents are built using a simple reasoning inspired by March and Olsen (2011) who posit that humans generally act as though they choose their actions by answering three key questions:
- What kind of situation is this?
- What kind of person am I?
- What does a person such as I do in a situation such as this?
The agents used in this example implement exactly these components, and nothing else.
If you use Concordia in your work, please cite the accompanying article:
@article{vezhnevets2023generative,
title={Generative agent-based modeling with actions grounded in physical,
social, or digital space using Concordia},
author={Vezhnevets, Alexander Sasha and Agapiou, John P and Aharon, Avia and
Ziv, Ron and Matyas, Jayd and Du{\'e}{\~n}ez-Guzm{\'a}n, Edgar A and
Cunningham, William A and Osindero, Simon and Karmon, Danny and
Leibo, Joel Z},
journal={arXiv preprint arXiv:2312.03664},
year={2023}
}
This is not an officially supported Google product.