Results 1 - 10 of 219,197

Learning to predict by the methods of temporal differences

by Richard S. Sutton - MACHINE LEARNING , 1988
"... This article introduces a class of incremental learning procedures specialized for prediction – that is, for using past experience with an incompletely known system to predict its future behavior. Whereas conventional prediction-learning methods assign credit by means of the difference between predi ..."
Abstract - Cited by 1521 (56 self) - Add to MetaCart
, they have remained poorly understood. Here we prove their convergence and optimality for special cases and relate them to supervised-learning methods. For most real-world prediction problems, temporal-difference methods require less memory and less peak computation than conventional methods and they produce

Self-discrepancy: A theory relating self and affect

by E. Tory Higgins - PSYCHOLOGICAL REVIEW , 1987
"... This article presents a theory of how different types of discrepancies between self-state representations are related to different kinds of emotional vulnerabilities. One domain of the self (actual; ideal; ought) and one standpoint on the self (own; significant other) constitute each type of self-st ..."
Abstract - Cited by 599 (7 self) - Add to MetaCart
This article presents a theory of how different types of discrepancies between self-state representations are related to different kinds of emotional vulnerabilities. One domain of the self (actual; ideal; ought) and one standpoint on the self (own; significant other) constitute each type of self

The “What” and “Why” of Goal Pursuits: Human Needs and the Self-Determination of Behavior

by Edward L. Deci, Richard M. Ryan , 2000
"... Self-determination theory (SDT) maintains that an understanding of human motiva-tion requires a consideration of innate psychological needs for competence, auton-omy, and relatedness. We discuss the SDT concept of needs as it relates to previous need theories, emphasizing that needs specify the nece ..."
Abstract - Cited by 1105 (36 self) - Add to MetaCart
relations to the quality of behavior and mental health, specifically be-cause different regulatory processes and different goal contents are associated with differing degrees of need satisfaction. Social contexts and individual differences that support satisfaction of the basic needs facilitate natural

The Askey-scheme of hypergeometric orthogonal polynomials and its q-analogue

by Roelof Koekoek, René F. Swarttouw , 1998
"... We list the so-called Askey-scheme of hypergeometric orthogonal polynomials and we give a q-analogue of this scheme containing basic hypergeometric orthogonal polynomials. In chapter 1 we give the definition, the orthogonality relation, the three term recurrence relation, the second order differenti ..."
Abstract - Cited by 578 (6 self) - Add to MetaCart
differential or difference equation, the forward and backward shift operator, the Rodrigues-type formula and generating functions of all classes of orthogonal polynomials in this scheme. In chapter 2 we give the limit relations between different classes of orthogonal polynomials listed in the Askey

Executive Compensation

by Kevin J. Murphy , 1999
"... This paper summarizes the empirical and theoretical research on executive compensation and provides a comprehensive and up-to-date description of pay practices (and trends in pay practices) for chief executive officers (CEOs). Topics discussed include the level and structure of CEO pay (including de ..."
Abstract - Cited by 625 (17 self) - Add to MetaCart
detailed analyses of annual bonus plans, executive stock options, and option valuation), international pay differences, the pay-setting process, the relation between CEO pay and firm performance (“pay-performance sensitivities”), the relation between sensitivities and subsequent firm performance, relative

A Survey on Sensor Networks

by Lan F. Akyildiz, Welljan Su, Yogesh Sankarasubramaniam, Erdal Cayirci , 2002
"... Recent advancement in wireless communica- tions and electronics has enabled the develop- ment of low-cost sensor networks. The sensor networks can be used for various application areas (e.g., health, military, home). For different application areas, there are different technical issues that research ..."
Abstract - Cited by 2002 (1 self) - Add to MetaCart
Recent advancement in wireless communica- tions and electronics has enabled the develop- ment of low-cost sensor networks. The sensor networks can be used for various application areas (e.g., health, military, home). For different application areas, there are different technical issues

Constraint Logic Programming: A Survey

by Joxan Jaffar, Michael J. Maher
"... Constraint Logic Programming (CLP) is a merger of two declarative paradigms: constraint solving and logic programming. Although a relatively new field, CLP has progressed in several quite different directions. In particular, the early fundamental concepts have been adapted to better serve in differe ..."
Abstract - Cited by 869 (25 self) - Add to MetaCart
Constraint Logic Programming (CLP) is a merger of two declarative paradigms: constraint solving and logic programming. Although a relatively new field, CLP has progressed in several quite different directions. In particular, the early fundamental concepts have been adapted to better serve

SPEA2: Improving the Strength Pareto Evolutionary Algorithm

by Eckart Zitzler, Marco Laumanns, Lothar Thiele , 2001
"... The Strength Pareto Evolutionary Algorithm (SPEA) (Zitzler and Thiele 1999) is a relatively recent technique for finding or approximating the Pareto-optimal set for multiobjective optimization problems. In different studies (Zitzler and Thiele 1999; Zitzler, Deb, and Thiele 2000) SPEA has shown very ..."
Abstract - Cited by 708 (19 self) - Add to MetaCart
The Strength Pareto Evolutionary Algorithm (SPEA) (Zitzler and Thiele 1999) is a relatively recent technique for finding or approximating the Pareto-optimal set for multiobjective optimization problems. In different studies (Zitzler and Thiele 1999; Zitzler, Deb, and Thiele 2000) SPEA has shown

Reinforcement Learning I: Introduction

by Richard S. Sutton, Andrew G. Barto , 1998
"... In which we try to give a basic intuitive sense of what reinforcement learning is and how it differs and relates to other fields, e.g., supervised learning and neural networks, genetic algorithms and artificial life, control theory. Intuitively, RL is trial and error (variation and selection, search ..."
Abstract - Cited by 5614 (118 self) - Add to MetaCart
In which we try to give a basic intuitive sense of what reinforcement learning is and how it differs and relates to other fields, e.g., supervised learning and neural networks, genetic algorithms and artificial life, control theory. Intuitively, RL is trial and error (variation and selection

Globally Consistent Range Scan Alignment for Environment Mapping

by F. Lu, E. Milios - AUTONOMOUS ROBOTS , 1997
"... A robot exploring an unknown environmentmay need to build a world model from sensor measurements. In order to integrate all the frames of sensor data, it is essential to align the data properly. An incremental approach has been typically used in the past, in which each local frame of data is alig ..."
Abstract - Cited by 531 (8 self) - Add to MetaCart
is aligned to a cumulative global model, and then merged to the model. Because different parts of the model are updated independently while there are errors in the registration, such an approachmay result in an inconsistent model. In this paper, we study the problem of consistent registration of multiple
Results 1 - 10 of 219,197