The Logic of Adaptive Behavior - Knowledge Representation and Algorithms for the Markov Decision Process Framework in First-Order Domains

M. van Otterlo

Research output: ThesisPhD Thesis - Research UT, graduation UT

Abstract

Learning and reasoning in large, structured, probabilistic worlds is at the heart of artificial intelligence. Markov decision processes have become the de facto standard in modeling and solving sequential decision making problems under uncertainty. Many efficient reinforcement learning and dynamic programming techniques exist that can solve such problems. Until recently, the representational state-of-the-art in this field was based on propositional representations. However, it is hard to imagine a truly general, intelligent system that does not conceive of the world in terms of objects and their properties and relations to other objects. To this end, this book studies lifting Markov decision processes, reinforcement learning and dynamic programming to the first-order (or, relational) setting. Based on an extensive analysis of propositional representations and techniques, a methodological translation is constructed from the propositional to the relational setting. Furthermore, this book provides a thorough and complete description of the state-of-the-art, it surveys vital, related historical developments and it contains extensive descriptions of several new model-free and model-based solution techniques.
LanguageUndefined
Awarding Institution
  • University of Twente
Supervisors/Advisors
  • Nijholt, Antinus , Supervisor
  • Poel, Mannes , Advisor
  • Meyer, J.J., Supervisor
  • Wiering, M.A., Supervisor
Award date30 May 2008
Place of PublicationEnschede
Print ISBNs978-90-365-2677-7
DOIs
StatePublished - 30 May 2008

Keywords

  • HMI-IA: Intelligent Agents
  • METIS-251036
  • IR-58987
  • EWI-12949

Cite this

@phdthesis{7c1dd155a0084647a4f595c60dde9679,
title = "The Logic of Adaptive Behavior - Knowledge Representation and Algorithms for the Markov Decision Process Framework in First-Order Domains",
abstract = "Learning and reasoning in large, structured, probabilistic worlds is at the heart of artificial intelligence. Markov decision processes have become the de facto standard in modeling and solving sequential decision making problems under uncertainty. Many efficient reinforcement learning and dynamic programming techniques exist that can solve such problems. Until recently, the representational state-of-the-art in this field was based on propositional representations. However, it is hard to imagine a truly general, intelligent system that does not conceive of the world in terms of objects and their properties and relations to other objects. To this end, this book studies lifting Markov decision processes, reinforcement learning and dynamic programming to the first-order (or, relational) setting. Based on an extensive analysis of propositional representations and techniques, a methodological translation is constructed from the propositional to the relational setting. Furthermore, this book provides a thorough and complete description of the state-of-the-art, it surveys vital, related historical developments and it contains extensive descriptions of several new model-free and model-based solution techniques.",
keywords = "HMI-IA: Intelligent Agents, METIS-251036, IR-58987, EWI-12949",
author = "{van Otterlo}, M.",
year = "2008",
month = "5",
day = "30",
doi = "10.3990/1.9789036526777",
language = "Undefined",
isbn = "978-90-365-2677-7",
school = "University of Twente",

}

The Logic of Adaptive Behavior - Knowledge Representation and Algorithms for the Markov Decision Process Framework in First-Order Domains. / van Otterlo, M.

Enschede, 2008. 496 p.

Research output: ThesisPhD Thesis - Research UT, graduation UT

TY - THES

T1 - The Logic of Adaptive Behavior - Knowledge Representation and Algorithms for the Markov Decision Process Framework in First-Order Domains

AU - van Otterlo,M.

PY - 2008/5/30

Y1 - 2008/5/30

N2 - Learning and reasoning in large, structured, probabilistic worlds is at the heart of artificial intelligence. Markov decision processes have become the de facto standard in modeling and solving sequential decision making problems under uncertainty. Many efficient reinforcement learning and dynamic programming techniques exist that can solve such problems. Until recently, the representational state-of-the-art in this field was based on propositional representations. However, it is hard to imagine a truly general, intelligent system that does not conceive of the world in terms of objects and their properties and relations to other objects. To this end, this book studies lifting Markov decision processes, reinforcement learning and dynamic programming to the first-order (or, relational) setting. Based on an extensive analysis of propositional representations and techniques, a methodological translation is constructed from the propositional to the relational setting. Furthermore, this book provides a thorough and complete description of the state-of-the-art, it surveys vital, related historical developments and it contains extensive descriptions of several new model-free and model-based solution techniques.

AB - Learning and reasoning in large, structured, probabilistic worlds is at the heart of artificial intelligence. Markov decision processes have become the de facto standard in modeling and solving sequential decision making problems under uncertainty. Many efficient reinforcement learning and dynamic programming techniques exist that can solve such problems. Until recently, the representational state-of-the-art in this field was based on propositional representations. However, it is hard to imagine a truly general, intelligent system that does not conceive of the world in terms of objects and their properties and relations to other objects. To this end, this book studies lifting Markov decision processes, reinforcement learning and dynamic programming to the first-order (or, relational) setting. Based on an extensive analysis of propositional representations and techniques, a methodological translation is constructed from the propositional to the relational setting. Furthermore, this book provides a thorough and complete description of the state-of-the-art, it surveys vital, related historical developments and it contains extensive descriptions of several new model-free and model-based solution techniques.

KW - HMI-IA: Intelligent Agents

KW - METIS-251036

KW - IR-58987

KW - EWI-12949

U2 - 10.3990/1.9789036526777

DO - 10.3990/1.9789036526777

M3 - PhD Thesis - Research UT, graduation UT

SN - 978-90-365-2677-7

CY - Enschede

ER -