Data

Tools

Indexes

Applications

Experiments

Open Source Science

safe-m3-ucrl

https://github.com/mjusup1501/safe-m3-ucrl

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: mjusup1501
  • License: bsd-3-clause
  • Language: Python
  • Default Branch: main
  • Size: 16.1 MB
Statistics
  • Stars: 7
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 1
Created about 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning Repository

DOI

To install required packages, run pip install -e .

In configs directory you can find config files for vehicle repositioning and swarm environments.

To run an experiment: 1. It is necessary to modify logdir field in a config file 2. For vehicle repositioning you must provide the demand and origin-destination matrices and modify inputdatapath in a config file. This step is not necessary for the swarm environment. 2. Optionally modify other fields, including entity for wandb logging or use pre-trained checkpoints that you can find in checkpoints directory 3. Execute python safe_mf/main.py --config path/to/config.yaml

Owner

  • Login: mjusup1501
  • Kind: user

Citation (CITATION.cff) 

cff-version: 0.0.1
message: "If you use this software, please cite it as below."
authors:
- family-names: "Jusup"
  given-names: "Matej"
  orcid: "https://orcid.org/0000-0002-3779-5041"
- family-names: "Janik"
  given-names: "Tadeusz"
title: "Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning"
version: 0.0.1
doi: 10.5281/zenodo.10431636
date-released: 2023-12-26
url: "https://github.com/mjusup1501/safe-m3-ucrl"

GitHub Events

Total
  • Push event: 3
  • Fork event: 1
Last Year
  • Push event: 3
  • Fork event: 1