Data

Tools

Indexes

Applications

Experiments

Open Source Science

drama-wrapper

Implementation of the governance wrapper paper for the 2024 HICSS conference.

https://github.com/michoest/drama-wrapper

Science Score: 44.0%

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
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.7%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Implementation of the governance wrapper paper for the 2024 HICSS conference.

Basic Info
  • Host: GitHub
  • Owner: michoest
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 27.9 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created about 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.rst 

.. raw:: html

    
DRAMA at the PettingZoo

    
Dynamically Restricted Action Spaces for
Multi-Agent Reinforcement Learning Frameworks


This repository contains the reference implementation of the *DRAMA*
framework as introduced in *Oesterle et al. (2024): DRAMA at the
PettingZoo: Dynamically Restricted Action Spaces for Multi-Agent
Reinforcement Learning Frameworks. Submitted to HICSS 2024.*

Installation
------------

To install the DRAMA library:

.. code-block::

    $  pip install drama-wrapper

Usage
-----

In analogy to the AEC of *PettingZoo*

.. code-block:: python

   env.reset()
   for agent in env.agent_iter():
       observation, reward, termination, truncation, info = env.last()
       action = env.action_space(agent).sample() # this is where you would insert your policy
       env.step(action)

the *DRAMA* loop can be imported and used as follows:

.. code-block:: python

   from drama.restrictors import Restrictor
   from drama.wrapper import RestrictionWrapper

   env = ...
   restrictor = Restrictor(...)
   wrapper = RestrictionWrapper(env, restrictor)
   policies = {...}

   wrapper.reset()
   for agent in wrapper.agent_iter():
       observation, reward, termination, truncation, info = wrapper.last()
       action = policies[agent](observation)
       wrapper.step(action)

Please refer to ``getting-started.ipynb`` for a first full example.

Documentation
-------------

The full documentation of the code can be found `here `__.

Citation
--------

To cite this project in a publication, please use

.. code-block::

   @misc{oesterle-2023-drama,
       author = {Oesterle, Michael and Grams, Tim},
       title = {DRAMA},
       year = {2023},
       url = {https://github.com/michoest/hicss-2024}
   }

or use the ``CITATION.cff`` file which is part of the package.

Owner

  • Name: Michael Oesterle
  • Login: michoest
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
title: DRAMA
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Michael
    family-names: Oesterle
    email: michael.oesterle@uni-mannheim.de
    affiliation: University of Mannheim
    orcid: 'https://orcid.org/0000-0001-6939-1028'
  - given-names: Tim
    family-names: Grams
    email: tim.grams339@outlook.de
    affiliation: University of Mannheim
    orcid: 'https://orcid.org/0009-0001-0248-0875'
repository-code: 'https://github.com/michoest/hicss-2024'
abstract: >-
  A PettingZoo-compatible framework for dynamically
  restricted action spaces for Multi-Agent Reinforcement
  Learning (MARL) frameworks.
keywords:
  - Multi-Agent Reinforcement Learning
  - Gymnasium
  - PettingZoo
  - Multi-Agent System
  - Action Space Restriction
license: MIT

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 15
  • Total pull requests: 2
  • Average time to close issues: about 2 months
  • Average time to close pull requests: 9 minutes
  • Total issue authors: 2
  • Total pull request authors: 1
  • Average comments per issue: 0.13
  • Average comments per pull request: 0.0
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • michoest (11)
  • tim-grams (4)
Pull Request Authors
  • tim-grams (2)
Top Labels
Issue Labels
feature (4) documentation (3) testing (1)
Pull Request Labels

Dependencies

docs/requirements.txt pypi
  • furo *
  • gymnasium *
  • numpy *
  • pettingzoo *
requirements.txt pypi
  • gymnasium *
  • numpy *
  • pettingzoo *
  • pygame *
  • seaborn *
  • shapely *
  • torch *
  • tqdm *
setup.py pypi
  • gymnasium *
  • numpy *
  • pettingzoo *