Standard

The MADP Toolbox : An Open Source Library for Planning and Learning in (Multi-)Agent Systems. / Oliehoek, Frans A.; Spaan, Matthijs T. J.; Terwijn, Bas; Robbel, Philipp; Messias, João V.

In: Journal of Machine Learning Research , Vol. 18, No. 89, 08.2017, p. 1-5.

Research output: Scientific - peer-reviewArticle

Harvard

Oliehoek, FA, Spaan, MTJ, Terwijn, B, Robbel, P & Messias, JV 2017, 'The MADP Toolbox: An Open Source Library for Planning and Learning in (Multi-)Agent Systems' Journal of Machine Learning Research , vol 18, no. 89, pp. 1-5.

APA

Oliehoek, F. A., Spaan, M. T. J., Terwijn, B., Robbel, P., & Messias, J. V. (2017). The MADP Toolbox: An Open Source Library for Planning and Learning in (Multi-)Agent Systems. Journal of Machine Learning Research , 18(89), 1-5.

Vancouver

Oliehoek FA, Spaan MTJ, Terwijn B, Robbel P, Messias JV. The MADP Toolbox: An Open Source Library for Planning and Learning in (Multi-)Agent Systems. Journal of Machine Learning Research . 2017 Aug;18(89):1-5.

Author

Oliehoek, Frans A. ; Spaan, Matthijs T. J. ; Terwijn, Bas ; Robbel, Philipp ; Messias, João V./ The MADP Toolbox : An Open Source Library for Planning and Learning in (Multi-)Agent Systems. In: Journal of Machine Learning Research . 2017 ; Vol. 18, No. 89. pp. 1-5

BibTeX

@article{6537c2eff3b64e7d89a0b5a7a65bab43,
title = "The MADP Toolbox: An Open Source Library for Planning and Learning in (Multi-)Agent Systems",
abstract = "This article describes the MultiAgent Decision Process (MADP) toolbox, a software library to support planning and learning for intelligent agents and multiagent systems in uncertain environments. Key features are that it supports partially observable environments and stochastic transition models; has unified support for single- and multiagent systems; provides a large number of models for decision-theoretic decision making, including one-shot and sequential decision making under various assumptions of observability and cooperation, such as Dec-POMDPs and POSGs; provides tools and parsers to quickly prototype new problems; provides an extensive range of planning and learning algorithms for single- and multiagent systems; it is released under a GNU GPL v3 license; and is written in C++ and designed to be extensible via the object-oriented paradigm.",
keywords = "software, decision-theoretic planning, reinforcement learning, multiagent systems",
author = "Oliehoek, {Frans A.} and Spaan, {Matthijs T. J.} and Bas Terwijn and Philipp Robbel and Messias, {João V.}",
year = "2017",
month = "8",
volume = "18",
pages = "1--5",
journal = "Journal of Machine Learning Research",
issn = "1532-4435",
publisher = "Microtome Publishing",
number = "89",

}

RIS

TY - JOUR

T1 - The MADP Toolbox

T2 - Journal of Machine Learning Research

AU - Oliehoek,Frans A.

AU - Spaan,Matthijs T. J.

AU - Terwijn,Bas

AU - Robbel,Philipp

AU - Messias,João V.

PY - 2017/8

Y1 - 2017/8

N2 - This article describes the MultiAgent Decision Process (MADP) toolbox, a software library to support planning and learning for intelligent agents and multiagent systems in uncertain environments. Key features are that it supports partially observable environments and stochastic transition models; has unified support for single- and multiagent systems; provides a large number of models for decision-theoretic decision making, including one-shot and sequential decision making under various assumptions of observability and cooperation, such as Dec-POMDPs and POSGs; provides tools and parsers to quickly prototype new problems; provides an extensive range of planning and learning algorithms for single- and multiagent systems; it is released under a GNU GPL v3 license; and is written in C++ and designed to be extensible via the object-oriented paradigm.

AB - This article describes the MultiAgent Decision Process (MADP) toolbox, a software library to support planning and learning for intelligent agents and multiagent systems in uncertain environments. Key features are that it supports partially observable environments and stochastic transition models; has unified support for single- and multiagent systems; provides a large number of models for decision-theoretic decision making, including one-shot and sequential decision making under various assumptions of observability and cooperation, such as Dec-POMDPs and POSGs; provides tools and parsers to quickly prototype new problems; provides an extensive range of planning and learning algorithms for single- and multiagent systems; it is released under a GNU GPL v3 license; and is written in C++ and designed to be extensible via the object-oriented paradigm.

KW - software

KW - decision-theoretic planning

KW - reinforcement learning

KW - multiagent systems

UR - http://resolver.tudelft.nl/uuid:6537c2ef-f3b6-4e7d-89a0-b5a7a65bab43

M3 - Article

VL - 18

SP - 1

EP - 5

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

SN - 1532-4435

IS - 89

ER -

ID: 34681360