This repo contains an implementation of Foundation, a framework for flexible, modular, and composable environments that model socio-economic behaviors and dynamics in a society with both agents and governments.
Foundation provides a Gym-style API:
reset: resets the environment's state and returns the observation.step: advances the environment by one timestep, and returns the tuple (observation, reward, done, info).
This simulation can be used in conjunction with reinforcement learning to learn optimal economic policies, as detailed in the following papers:
The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies, Stephan Zheng, Alexander Trott, Sunil Srinivasa, Nikhil Naik, Melvin Gruesbeck, David C. Parkes, Richard Socher.
The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning Stephan Zheng, Alexander Trott, Sunil Srinivasa, David C. Parkes, Richard Socher.
Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist Alexander Trott, Sunil Srinivasa, Douwe van der Wal, Sebastien Haneuse, Stephan Zheng.
If you use this code in your research, please cite us using this BibTeX entry:
@misc{2004.13332,
Author = {Stephan Zheng, Alexander Trott, Sunil Srinivasa, Nikhil Naik, Melvin Gruesbeck, David C. Parkes, Richard Socher},
Title = {The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies},
Year = {2020},
Eprint = {arXiv:2004.13332},
}
For more information and context, check out:
- The AI Economist website
- Blog: The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
- Blog: The AI Economist moonshot
- Blog: The AI Economist web demo of the COVID-19 case study
- Web demo: The AI Economist ethical review of AI policy design and COVID-19 case study
Please see our Simulation Card for a review of the intended use and ethical review of our framework.
Please see our COVID-19 Simulation Card for a review of the ethical aspects of the pandemic simulation (and as fitted for COVID-19).
If you're interested in extending this framework, discussing machine learning for economics, and collaborating on research project:
- join our Slack channel aieconomist.slack.com using this invite link, or
- email us @ ai.economist@salesforce.com.
To get started, you'll need to have Python 3.7+ installed.
Simply use the Python package manager:
pip install ai-economist- Clone this repository to your local machine:
git clone www.github.com/salesforce/ai-economist
- Create a new conda environment (named "ai-economist" below - replace with anything else) and activate it
conda create --name ai-economist python=3.7 --yes
conda activate ai-economist
-
Either
a) Edit the PYTHONPATH to include the ai-economist directory
export PYTHONPATH=<local path to ai-economist>:$PYTHONPATH
OR
b) Install as an editable Python package
cd ai-economist
pip install -e .
Useful tip: for quick access, add the following to your ~/.bashrc or ~/.bash_profile:
alias aiecon="conda activate ai-economist; cd <local path to ai-economist>"
You can then simply run aiecon once to activate the conda environment.
To test your installation, try running:
conda activate ai-economist
python -c "import ai_economist"
To familiarize yourself with Foundation, check out the tutorials in the tutorials folder. You can run these notebooks interactively in your browser on Google Colab.
- economic_simulation_basic (Try this on Colab!): Shows how to interact with and visualize the simulation.
- economic_simulation_advanced (Try this on Colab!): Explains how Foundation is built up using composable and flexible building blocks.
- optimal_taxation_theory_and_simulation (Try this on Colab!): Demonstrates how economic simulations can be used to study the problem of optimal taxation.
- covid19_and_economic_simulation (Try this on Colab!): Introduces a simulation on the COVID-19 pandemic and economy that can be used to study different health and economic policies .
- multi_agent_gpu_training_with_warp_drive (Try this on Colab!): Introduces our multi-agent reinforcement learning framework WarpDrive, which we then use to train the COVID-19 and economic simulation.
- multi_agent_training_with_rllib (Try this on Colab!): Shows how to perform distributed multi-agent reinforcement learning with RLlib.
- two_level_curriculum_training_with_rllib: Describes how to implement two-level curriculum training with RLlib.
To run these notebooks locally, you need Jupyter. See https://jupyter.readthedocs.io/en/latest/install.html for installation instructions and (https://jupyter-notebook.readthedocs.io/en/stable/ for examples of how to work with Jupyter.
- The simulation is located in the
ai_economist/foundationfolder.
The code repository is organized into the following components:
| Component | Description |
|---|---|
| base | Contains base classes to can be extended to define Agents, Components and Scenarios. |
| agents | Agents represent economic actors in the environment. Currently, we have mobile Agents (representing workers) and a social planner (representing a government). |
| entities | Endogenous and exogenous components of the environment. Endogenous entities include labor, while exogenous entity includes landmarks (such as Water and Grass) and collectible Resources (such as Wood and Stone). |
| components | Components are used to add some particular dynamics to an environment. They also add action spaces that define how Agents can interact with the environment via the Component. |
| scenarios | Scenarios compose Components to define the dynamics of the world. It also computes rewards and exposes states for visualization. |
- The datasets (including the real-world data on COVID-19) are located in the
ai_economist/datasetsfolder.
- Please let us know if you encounter any bugs by filing a GitHub issue.
- We appreciate all your contributions. If you plan to contribute new Components, Scenarios Entities, or anything else, please see our contribution guidelines.
For the complete release history, see CHANGELOG.md.
Foundation and the AI Economist are released under the BSD-3 License.