Author: Jonathan Matthew Gratch
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 32
Book Description
It is also clear that these systems make strong assumptions about the topography of the search space, like guaranteed ascent, which we argue are violated. While our focus is on learning control strategies, the issues are relevant to the study of control knowledge in general."
A Framework for Evaluating Search Control Strategies
Author: Jonathan Matthew Gratch
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 32
Book Description
It is also clear that these systems make strong assumptions about the topography of the search space, like guaranteed ascent, which we argue are violated. While our focus is on learning control strategies, the issues are relevant to the study of control knowledge in general."
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 32
Book Description
It is also clear that these systems make strong assumptions about the topography of the search space, like guaranteed ascent, which we argue are violated. While our focus is on learning control strategies, the issues are relevant to the study of control knowledge in general."
Artificial Intelligence Planning Systems
Author: James Hendler
Publisher: Elsevier
ISBN: 0080499449
Category : Computers
Languages : en
Pages : 327
Book Description
Artificial Intelligence Planning Systems documents the proceedings of the First International Conference on AI Planning Systems held in College Park, Maryland on June 15-17, 1992. This book discusses the abstract probabilistic modeling of action; building symbolic primitives with continuous control routines; and systematic adaptation for case-based planning. The analysis of ABSTRIPS; conditional nonlinear planning; and building plans to monitor and exploit open-loop and closed-loop dynamics are also elaborated. This text likewise covers the modular utility representation for decision-theoretic planning; reaction and reflection in tetris; and planning in intelligent sensor fusion. Other topics include the resource-bounded adaptive agent, critical look at Knoblock's hierarchy mechanism, and traffic laws for mobile robots. This publication is beneficial to students and researchers conducting work on AI planning systems.
Publisher: Elsevier
ISBN: 0080499449
Category : Computers
Languages : en
Pages : 327
Book Description
Artificial Intelligence Planning Systems documents the proceedings of the First International Conference on AI Planning Systems held in College Park, Maryland on June 15-17, 1992. This book discusses the abstract probabilistic modeling of action; building symbolic primitives with continuous control routines; and systematic adaptation for case-based planning. The analysis of ABSTRIPS; conditional nonlinear planning; and building plans to monitor and exploit open-loop and closed-loop dynamics are also elaborated. This text likewise covers the modular utility representation for decision-theoretic planning; reaction and reflection in tetris; and planning in intelligent sensor fusion. Other topics include the resource-bounded adaptive agent, critical look at Knoblock's hierarchy mechanism, and traffic laws for mobile robots. This publication is beneficial to students and researchers conducting work on AI planning systems.
Innovative Approaches to Planning, Scheduling and Control
Author: Katia P. Sycara
Publisher: Morgan Kaufmann
ISBN: 9781558601642
Category : Computers
Languages : en
Pages : 532
Book Description
Publisher: Morgan Kaufmann
ISBN: 9781558601642
Category : Computers
Languages : en
Pages : 532
Book Description
Machine Learning Methods for Planning
Author: Steven Minton
Publisher: Morgan Kaufmann
ISBN: 1483221172
Category : Social Science
Languages : en
Pages : 555
Book Description
Machine Learning Methods for Planning provides information pertinent to learning methods for planning and scheduling. This book covers a wide variety of learning methods and learning architectures, including analogical, case-based, decision-tree, explanation-based, and reinforcement learning. Organized into 15 chapters, this book begins with an overview of planning and scheduling and describes some representative learning systems that have been developed for these tasks. This text then describes a learning apprentice for calendar management. Other chapters consider the problem of temporal credit assignment and describe tractable classes of problems for which optimal plans can be derived. This book discusses as well how reactive, integrated systems give rise to new requirements and opportunities for machine learning. The final chapter deals with a method for learning problem decompositions, which is based on an idealized model of efficiency for problem-reduction search. This book is a valuable resource for production managers, planners, scientists, and research workers.
Publisher: Morgan Kaufmann
ISBN: 1483221172
Category : Social Science
Languages : en
Pages : 555
Book Description
Machine Learning Methods for Planning provides information pertinent to learning methods for planning and scheduling. This book covers a wide variety of learning methods and learning architectures, including analogical, case-based, decision-tree, explanation-based, and reinforcement learning. Organized into 15 chapters, this book begins with an overview of planning and scheduling and describes some representative learning systems that have been developed for these tasks. This text then describes a learning apprentice for calendar management. Other chapters consider the problem of temporal credit assignment and describe tractable classes of problems for which optimal plans can be derived. This book discusses as well how reactive, integrated systems give rise to new requirements and opportunities for machine learning. The final chapter deals with a method for learning problem decompositions, which is based on an idealized model of efficiency for problem-reduction search. This book is a valuable resource for production managers, planners, scientists, and research workers.
Proceedings of the Eleventh National Conference on Artificial Intelligence
Author: American Association for Artificial Intelligence
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 930
Book Description
AAAI proceedings describe innovative concepts, techniques, perspectives, and observations that present promising research directions in artificial intelligence.Topics include: The principles underlying cognition, perception, and action in humans' and machines. The design, application, and evaluation of AI algorithms and intelligent systems. The analysis of tasks and domains in which intelligent systems perform.
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 930
Book Description
AAAI proceedings describe innovative concepts, techniques, perspectives, and observations that present promising research directions in artificial intelligence.Topics include: The principles underlying cognition, perception, and action in humans' and machines. The design, application, and evaluation of AI algorithms and intelligent systems. The analysis of tasks and domains in which intelligent systems perform.
An Analysis of Learning to Plan as a Search Problem
Author: Jonathan Matthew Gratch
Publisher:
ISBN:
Category : Machine learning
Languages : en
Pages : 38
Book Description
These 'learning operators' define a space of possible transformations through which a system must search for a [sic] efficient planner. We show that the complexity of this search precludes a general solution and can only be approached via simplifications. We illustrate the frequently unarticulated commitments which underly current learning approaches. These simplifications improve learning efficiency but not without tradeoffs. In some cases these tradeoffs result in less than optimal behavior. In others, they produce planners which become worse through learning. It is hoped that by articulating these commitments we can better understand their ramifications.
Publisher:
ISBN:
Category : Machine learning
Languages : en
Pages : 38
Book Description
These 'learning operators' define a space of possible transformations through which a system must search for a [sic] efficient planner. We show that the complexity of this search precludes a general solution and can only be approached via simplifications. We illustrate the frequently unarticulated commitments which underly current learning approaches. These simplifications improve learning efficiency but not without tradeoffs. In some cases these tradeoffs result in less than optimal behavior. In others, they produce planners which become worse through learning. It is hoped that by articulating these commitments we can better understand their ramifications.
New Directions in AI Planning
Author: Malik Ghallab
Publisher:
ISBN: 9784274900648
Category : Artificial intelligence
Languages : en
Pages : 422
Book Description
Publisher:
ISBN: 9784274900648
Category : Artificial intelligence
Languages : en
Pages : 422
Book Description
COMPOSER
Author: Jonathan Matthew Gratch
Publisher:
ISBN:
Category : Machine learning
Languages : en
Pages : 34
Book Description
Abstract: "In machine learning there is considerable interest in techniques which improve planning ability. Initial investigations have identified a wide variety of techniques to address this issue. Progress has been hampered by the utility problem, a basic tradeoff between the benefit of learned knowledge and the cost to locate and apply relevant knowledge. In this paper we describe the COMPOSER system. COMPOSER embodies a probabilistic solution to the utility problem. It is implemented in the PRODIGY architecture. We compare COMPOSER to four other approaches which appear in the literature."
Publisher:
ISBN:
Category : Machine learning
Languages : en
Pages : 34
Book Description
Abstract: "In machine learning there is considerable interest in techniques which improve planning ability. Initial investigations have identified a wide variety of techniques to address this issue. Progress has been hampered by the utility problem, a basic tradeoff between the benefit of learned knowledge and the cost to locate and apply relevant knowledge. In this paper we describe the COMPOSER system. COMPOSER embodies a probabilistic solution to the utility problem. It is implemented in the PRODIGY architecture. We compare COMPOSER to four other approaches which appear in the literature."
Proceedings of the Ninth International Joint Conference on Artificial Intelligence
Author: International Joint Conferences on Artificial Intelligence
Publisher: Elsevier
ISBN: 9780934613026
Category : Artificial Intelligence
Languages : en
Pages : 1368
Book Description
Publisher: Elsevier
ISBN: 9780934613026
Category : Artificial Intelligence
Languages : en
Pages : 1368
Book Description
Artificial Intelligence Planning Systems
Author: James A. Hendler
Publisher: Morgan Kaufmann
ISBN:
Category : Computers
Languages : en
Pages : 346
Book Description
Publisher: Morgan Kaufmann
ISBN:
Category : Computers
Languages : en
Pages : 346
Book Description