This repository contains the code for the paper "Shallow Planning under Partial Observability". The code provides multiple experiments to reproduce the results presented in the paper and better understand the impact of partial observability on shallow planning.
This file lists the Python dependencies required to run the code in this repository. The dependencies include:
numpy: A fundamental package for scientific computing with Python.matplotlib: A plotting library for creating static, animated, and interactive visualizations in Python.pymdptoolbox: A Python library for Markov Decision Processes (MDP) tools.joblib: A set of tools to provide lightweight pipelining in Python.
For a detailed explanation of the methodologies, experiments, and results, please refer to the article associated with this project: Pending, anonymous
-
Clone the repository:
git clone https://github.com/yourusername/shallow_planning_partial_observability.git cd shallow_planning_partial_observability -
Install the required dependencies:
pip install -r requirements.txt
-
Run the code and explore the results: Each Jupyter Notebook (.ipynb) file contains the code for a specific experiment. To run an experiment, open the notebook using Jupyter Notebook or JupyterLab. You can start Jupyter Notebook with the following command:
jupyter notebook
This will open a new tab in your web browser where you can navigate to the desired .ipynb file and run the cells sequentially to execute the experiment.
Feel free to explore the code and modify it to suit your needs. If you have any questions or encounter any issues, please open an issue on GitHub.
This project is licensed under the MIT License.