Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
MeanFieldwithGlobalState/README.md
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
56 lines (41 sloc)
1.74 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Introduction | |
This repository contains codes that are used for generating numerical results in the following paper: | |
"Mean-Field Control based Approximation of Multi-Agent Reinforcement Learning in Presence of a Shared Global State", | |
Transactions on Machine Learning Research, May, 2023. | |
[[arXiv]](https://arxiv.org/abs/2301.06889) [[TMLR]](https://openreview.net/forum?id=ZME2nZMTvY) | |
``` | |
@article{mondal2023mean, | |
title={Mean-Field Control based Approximation of Multi-Agent Reinforcement Learning in Presence of a Non-decomposable Shared Global State}, | |
author={Mondal, Washim Uddin and Aggarwal, Vaneet and Ukkusuri, Satish V}, | |
journal={arXiv preprint arXiv:2301.06889}, | |
year={2023} | |
} | |
``` | |
# Parameters | |
Various parameters used in the experiments can be found in [Scripts/Parameters.py](https://github.itap.purdue.edu/Clan-labs/MeanFieldwithGlobalState/blob/main/Scripts/Parameters.py) file. | |
# Software and Packages | |
``` | |
python 3.8.12 | |
pytorch 1.10.1 | |
numpy 1.21.2 | |
matplotlib 3.5.0 | |
``` | |
# Results | |
Generated results will be stored in Results folder (will be created on the fly). | |
Some pre-generated results are available for display in the Display folder. Specifically, | |
[Fig. 1](https://github.itap.purdue.edu/Clan-labs/MeanFieldwithGlobalState/blob/main/Display/Fig1.png) depicts the error as a function | |
of N (the number of agents). | |
# Run Experiments | |
``` | |
python3 Main.py | |
``` | |
The progress of the experiment is logged in Results/progress.log | |
# Command Line Options | |
Various command line options are given below: | |
``` | |
--train : if training is required from scratch, otherwise a pre-trained model will be used | |
--minN : minimum value of N | |
--numN : number of N values | |
--divN : difference between two consecutive N values | |
--maxSeed: number of random seeds | |
``` |