CITATION.cff

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
title: "RLagentLudo: A Research-Grade Framework for Training RL Agents in Ludo"
version: 0.1.0
date-released: 2024-12-19
authors:
  - given-names: Hitesh
    family-names: Balegar
    email: hiteshbalegar@gmail.com
abstract: "A research-grade experimental framework for training and comparing reinforcement learning agents in the board game Ludo. The framework includes a curriculum of progressively complex game variants, implementations of DQN and T-REX algorithms, and comprehensive tooling for preference-based reward learning."
keywords:
  - reinforcement learning
  - deep Q-network
  - T-REX
  - preference learning
  - board games
  - Ludo
  - curriculum learning
  - reward learning
license: Apache-2.0
repository-code: "https://github.com/loadingname/RLagentLudo"
url: "https://github.com/loadingname/RLagentLudo"

references:
  # Academic Papers
  - type: generic
    title: "Policy invariance under reward transformations: Theory and application to reward shaping"
    authors:
      - family-names: Ng
        given-names: Andrew Y.
      - family-names: Harada
        given-names: Daishi
      - family-names: Russell
        given-names: Stuart
    year: 1999
    venue: "ICML"
    keywords:
      - reward shaping
      - potential-based reward shaping
      - PBRS
      - reinforcement learning

  - type: generic
    title: "Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations"
    authors:
      - family-names: Brown
        given-names: Daniel
      - family-names: Goo
        given-names: Wonjoon
      - family-names: Nagarajan
        given-names: Prabhat
      - family-names: Niekum
        given-names: Scott
    year: 2019
    venue: "ICML"
    keywords:
      - T-REX
      - trajectory-ranked reward extrapolation
      - inverse reinforcement learning
      - preference learning

  - type: article
    title: "Human-level control through deep reinforcement learning"
    authors:
      - family-names: Mnih
        given-names: Volodymyr
      - family-names: Kavukcuoglu
        given-names: Koray
      - family-names: Silver
        given-names: David
      - family-names: Graves
        given-names: Alex
      - family-names: Antonoglou
        given-names: Ioannis
      - family-names: Wierstra
        given-names: Daan
      - family-names: Riedmiller
        given-names: Martin
    year: 2015
    journal: "Nature"
    volume: 518
    issue: 7540
    start: 529
    end: 533
    keywords:
      - DQN
      - deep Q-network
      - reinforcement learning
      - Atari

  - type: generic
    title: "Dueling network architectures for deep reinforcement learning"
    authors:
      - family-names: Wang
        given-names: Ziyu
      - family-names: Schaul
        given-names: Tom
      - family-names: Hessel
        given-names: Matteo
      - family-names: Van Hasselt
        given-names: Hado
      - family-names: Lanctot
        given-names: Marc
      - family-names: Freitas
        given-names: Nando
    year: 2016
    venue: "ICML"
    keywords:
      - dueling network
      - deep reinforcement learning
      - value function approximation

  # Software and Libraries
  - type: software
    title: "Gymnasium: A Standard Interface for Reinforcement Learning Environments"
    authors:
      - given-names: Mark
        family-names: Towers
        email: mt5g17@soton.ac.uk
        affiliation: University of Southampton & Farama Foundation
        orcid: 'https://orcid.org/0000-0002-2609-2041'
      - given-names: Ariel
        family-names: Kwiatkowski
        email: akwiatkowski@farama.org
        affiliation: Farama Foundation
        orcid: 'https://orcid.org/0000-0002-9391-9993'
      - given-names: Jordan K
        family-names: Terry
        email: jkterry@farama.org
        affiliation: Farama Foundation
        orcid: 'https://orcid.org/0009-0006-4511-3756'
      - given-names: John U.
        family-names: Balis
        email: balis@wisc.edu
        affiliation: Independent Researcher
      - given-names: Gianluca
        name-particle: de
        family-names: Cola
        email: gianluca.deco@gmail.com
        affiliation: Farama Foundation
      - given-names: Tristan
        family-names: Deleu
        email: deleutri@mila.quebec
        affiliation: 'Mila, Université de Montréal'
      - given-names: Manuel
        family-names: Goulão
        email: manuel.silva.goulao@tecnico.ulisboa.pt
        affiliation: NeuralShift
        orcid: 'https://orcid.org/0000-0001-6478-2038'
      - given-names: Andreas
        family-names: Kallinteris
        email: akallinteris@tuc.gr
        affiliation: Technical University of Crete (TUC)
        orcid: 'https://orcid.org/0000-0002-6223-2670'
      - given-names: Markus
        family-names: Krimmel
        email: markus.krimmel@student.uni-tuebingen.de
        affiliation: Independent Researcher
        orcid: 'https://orcid.org/0009-0005-0159-1214'
      - given-names: Arjun
        email: kg.arjun@gmail.com
        family-names: KG
        affiliation: EarthBrain
      - given-names: Rodrigo
        family-names: Perez-Vicente
        email: rperezvicente@farama.org
        affiliation: Farama Foundation
      - given-names: Andrea
        family-names: Pierré
        email: andrea_pierre@brown.edu
        affiliation: Brown University
        orcid: 'https://orcid.org/0000-0003-4501-5428'
      - given-names: Sander
        family-names: Schulhoff
        email: sschulho@umd.edu
        affiliation: University of Maryland
        orcid: 'https://orcid.org/0009-0003-1904-0838'
      - given-names: Jun Jet
        family-names: Tai
        email: taijunjet@hotmail.com
        affiliation: Coventry University
      - given-names: Hannah Jin Shen
        family-names: Tan
        email: andrew.jinshen@gmail.com
        orcid: 'https://orcid.org/0009-0009-8772-5525'
        affiliation: Independent Researcher
      - given-names: Omar G.
        family-names: Younis
        email: omar.younis98@gmail.com
        affiliation: University of Bologna
        orcid: 'https://orcid.org/0009-0004-2783-7932'
    identifiers:
      - type: url
        value: 'https://arxiv.org/abs/2407.17032'
    repository-code: 'https://github.com/Farama-Foundation/Gymnasium'
    url: 'https://gymnasium.farama.org/'
    abstract: >-
    Gymnasium is an open-source library providing an API for
    reinforcement learning environments. Its main contribution
    is a central abstraction for wide interoperability between
    benchmark environments and training algorithms. Gymnasium
    comes with various built-in environments and utilities to
    simplify researchers’ work along with being supported by
    most training libraries. This paper outlines the main
    design decisions for Gymnasium, its key features, and the
    differences to alternative APIs.
    keywords:
      - reinforcement learning
      - machine learning
      - artificial intelligence
      - simulation
    year: 2023

  - type: software
    title: "PyTorch: An open source machine learning framework"
    authors:
      - name: "PyTorch Team"
    year: 2023
    url: "https://pytorch.org/"
    repository-code: "https://github.com/pytorch/pytorch"
    keywords:
      - machine learning
      - deep learning
      - pytorch
      - neural networks

  # Code Repositories
  - type: software
    title: "AI-Ludo"
    authors:
      - family-names: Sangrasi
        given-names: Mehran
    repository-code: "https://github.com/MehranSangrasi/AI-Ludo"
    url: "https://github.com/MehranSangrasi/AI-Ludo"
    keywords:
      - Ludo
      - AI
      - board game

  - type: software
    title: "Ludo_Game_AI"
    authors:
      - family-names: Aurucci
        given-names: Raffaele
    repository-code: "https://github.com/raffaele-aurucci/Ludo_Game_AI"
    url: "https://github.com/raffaele-aurucci/Ludo_Game_AI"
    keywords:
      - Ludo
      - game AI
      - board game