https://github.com/valinsogna/govtaxoptimal_rl
RL framework designed to simulate and optimize government taxation policies. Focused on balancing economic equality and consumption, it employs state-of-the-art RL algorithms, PPO and SAC, to navigate wealth taxation strategies across various economic scenarios, aiming to achieve optimal wealth distribution and economic efficiency.
https://github.com/valinsogna/govtaxoptimal_rl
heterogeneous-agent ppo reinforcement-learning sac taxation-policy
Last synced: 7 months ago
JSON representation
RL framework designed to simulate and optimize government taxation policies. Focused on balancing economic equality and consumption, it employs state-of-the-art RL algorithms, PPO and SAC, to navigate wealth taxation strategies across various economic scenarios, aiming to achieve optimal wealth distribution and economic efficiency.
- Host: GitHub
- URL: https://github.com/valinsogna/govtaxoptimal_rl
- Owner: valinsogna
- License: apache-2.0
- Created: 2024-03-18T20:53:13.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-04-12T12:12:16.000Z (over 1 year ago)
- Last Synced: 2025-01-22T15:36:40.373Z (9 months ago)
- Topics: heterogeneous-agent, ppo, reinforcement-learning, sac, taxation-policy
- Language: Jupyter Notebook
- Homepage:
- Size: 35.3 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TaxationPolicyRL
## Overview
TaxationPolicyRL is a Reinforcement Learning (RL) project focused on simulating and optimizing wealth taxation policies using various RL algorithms. The project utilizes a custom Gym environment to model the taxation system and applies algorithms like PPO and SAC to optimize policy decisions.
This project was supervised by collaboration with researchers form **Bank of Italy** Aldo Glielmo and Valerio Astuti.
## Installation
### Prerequisites
- Python 3.8 or higher
- pip (Python package manager)
### Steps
1. Clone the Repository
```bash
git clone https://github.com/valinsogna/GovTaxOptimal_RL.git
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
## Usage
### Configuration
- Modify the `config.py` to change model configurations, including the choice of RL algorithm, policy type, and total timesteps.
- Enable or disable Weights & Biases logging through the configuration prompts.
### Training the Model
- Run the main script to start training:
```bash
python main.py
```
- Run the main script with settings configured in config.json file:
```bash
python main.py -f config.json
```
### Evaluation
- The project includes an evaluation script to assess the performance of the trained model.
### Project Structure
- `src/`: Source code for the project including the RL models and utilities.
- `TaxationEnv.py`: Custom Gym environment for the taxation policy simulation.
- `model.py`: Model manager for initializing various RL models.
- `config.py`: Configuration script for setting up model parameters and options.
- `requirements.txt`: List of dependencies for the project.
- `README.md`: This file, containing project information and instructions.
- `results/`: Folder for results storage.
- `baseline/`: Comparable baseline algorithm Multi-Objective PSO.
## Acknowledgments
I extend my deepest gratitude to the Banca d'Italia for their invaluable collaboration on the TaxationPolicyRL project. Special thanks are due to **Aldo Glielmo** and **Valerio Astuti** from the **ART division** for their expert insights and contributions. Their support and guidance were instrumental in shaping the research and outcomes of this project.