Results 11  20
of
43
Towards Flexible MultiAgent DecisionMaking Under Time Pressure
 In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
, 1999
"... To perform rational decisionmaking, autonomous agents need considerable computational resources. In multiagent settings, when other agents are present in the environment, these demands are even more severe. We investigate ways in which the agent's knowledge and the results of deliberative decision ..."
Abstract

Cited by 5 (3 self)
 Add to MetaCart
To perform rational decisionmaking, autonomous agents need considerable computational resources. In multiagent settings, when other agents are present in the environment, these demands are even more severe. We investigate ways in which the agent's knowledge and the results of deliberative decisionmaking can be compiled to reduce the complexity of decisionmaking procedures and to save time in urgent situations. We use machine learning algorithms to compile decisiontheoretic deliberations into conditionaction rules on how to coordinate in a multiagent environment. Using different learning algorithms, we endow a resourcebounded agent with a tapestry of decision making tools, ranging from purely reactive to fully deliberative ones. The agent can then select a method depending on the time constraints of the particular situation. We also propose combining the decisionmaking tools, so that, for example, more reactive methods serve as a preprocessing stage to the more accurate but sl...
Valuation of Projects and Real Options in Incomplete Markets
, 2004
"... This thesis presents a framework for valuing risky projects and its extension for the valuation of real options and managerial flexibility. The framework is also applied in a case where the investor's probability estimates are imprecise or unknown. ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
This thesis presents a framework for valuing risky projects and its extension for the valuation of real options and managerial flexibility. The framework is also applied in a case where the investor's probability estimates are imprecise or unknown.
UtilityBased Categorization
, 1993
"... The ability to categorize and use concepts e#ectively is a basic requirementofany intelligent actor. The utilitybased approach to categorization is founded on the thesis that categorization is fundamentally in service of action, i.e., the choice of concepts made by an actor is critical to its choi ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
The ability to categorize and use concepts e#ectively is a basic requirementofany intelligent actor. The utilitybased approach to categorization is founded on the thesis that categorization is fundamentally in service of action, i.e., the choice of concepts made by an actor is critical to its choice of appropriate actions. This is in contrast to classical and similaritybased approaches which seek logical completeness in concept description with respect to sensory data rather than actionoriented e#ectiveness. Utilitybased categorization is normative and not descriptive. It prescribes howanintelligent agent ought to conceptualize to act e#ectively. It provides ideals for categorization, speci#es criteria for the design of e#ective computational agents, and provides a model of ideal competence. A decisiontheoretic framework for utilitybased categorization whichinvolves reasoning about alternative categorization models of varying levels of abstraction is proposed. Categorization mode...
StateBased Reconstructability Modeling for Decision Analysis
 In: Proceedings of World Congress of the Systems Sciences and International Society for the Systems Sciences 2000
, 2000
"... Reconstructability analysis (RA) is a method for detecting and analyzing the structure of multivariate categorical data. Jones and his colleagues extended the original variablebased formulation of RA to encompass models defined in terms of system states (Jones ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
Reconstructability analysis (RA) is a method for detecting and analyzing the structure of multivariate categorical data. Jones and his colleagues extended the original variablebased formulation of RA to encompass models defined in terms of system states (Jones
Framework for Measuring Rationale Clarity of AEC Design Decisions
, 2008
"... Current Architecture, Engineering, and Construction (AEC) design processes rely on precedent to resolve complex decisions. However, changing stakeholder concerns, design methods, and building products negate much of this precedent knowledge. Project teams need to clearly communicate their decision r ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
Current Architecture, Engineering, and Construction (AEC) design processes rely on precedent to resolve complex decisions. However, changing stakeholder concerns, design methods, and building products negate much of this precedent knowledge. Project teams need to clearly communicate their decision rationale in order to develop consensus about design decisions. The AEC industry requires a new framework to evaluate decision making. This paper builds on a broad range of theory including DecisionBased Design, Decision Analysis, Decision Theory, linguistics, logic, organization theory, and social welfare. First, this paper describes rationale as a set of assertions regarding distinct components (i.e. managers, stakeholders, designers, gatekeepers, objectives, constraints, options, and analysis) that support design decisions. Second, this paper describes conditions of clarity (i.e. coherent, concrete, connected, consistent, convincing, certain, and correct). These are used to measure the clarity of assertions, components, and the rationale as a whole. Taken together, this Rationale Clarity Framework (RCF) enables an objective evaluation of existing decision support methods. RCF provides a broad yet structured view for assessing process, organization, and product performance and for assessing AEC industry dynamics.
Sensitivity analysis in decision circuits
"... Decision circuits have been developed to perform efficient evaluation of influence diagrams [Bhattacharjya and Shachter, 2007], building on the advances in arithmetic circuits for belief network inference [Darwiche, 2003]. In the process of model building and analysis, we perform sensitivity analysi ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Decision circuits have been developed to perform efficient evaluation of influence diagrams [Bhattacharjya and Shachter, 2007], building on the advances in arithmetic circuits for belief network inference [Darwiche, 2003]. In the process of model building and analysis, we perform sensitivity analysis to understand how the optimal solution changes in response to changes in the model. When sequential decision problems under uncertainty are represented as decision circuits, we can exploit the efficient solution process embodied in the decision circuit and the wealth of derivative information available to compute the value of information for the uncertainties in the problem and the effects of changes to model parameters on the value and the optimal strategy. 1
New Tools for Decision Analysts
"... Abstract—This paper presents psychological research that can help people make better decisions. Decision analysts typically: 1) elicit outcome probabilities; 2) assess attribute weights; and 3) suggest the option with the highest overall value. Decision analysis can be challenging because of environ ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Abstract—This paper presents psychological research that can help people make better decisions. Decision analysts typically: 1) elicit outcome probabilities; 2) assess attribute weights; and 3) suggest the option with the highest overall value. Decision analysis can be challenging because of environmental and psychological issues. Fast and frugal methods such as natural frequency formats, frugal multiattribute models, and fast and frugal decision trees can address these issues. Not only are the methods fast and frugal, but they can also produce results that are surprisingly close to or even better than those obtained by more extensive analysis. Apart from raising awareness of these findings among engineers, the authors also call for further research on the application of fast and frugal methods to decision analysis. Index Terms—Adaptive decision making, decision analysis, fast and frugal heuristics, fast and frugal trees, natural frequency formats. I.
Utilityprobability duality
, 2004
"... This paper introduces duality between probability distributions and utility functions. The primal problem is to maximize the expected utility over a set of probability distributions. To develop the dual problem, we scale the utility function between zero and one, so that it obeys the same mathematic ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This paper introduces duality between probability distributions and utility functions. The primal problem is to maximize the expected utility over a set of probability distributions. To develop the dual problem, we scale the utility function between zero and one, so that it obeys the same mathematical properties as a (cumulative) probability function. We show that reversing the roles of the two functions in the expected utility formulation provides a natural “dual ” problem. Many of the known results for the primal problem can be reinterpreted in the dual problem. For example, we introduce a new quantity, the aspiration equivalent, as the “dual ” of the certain equivalent. The aspiration equivalent provides a new method for choosing between lotteries and a winwin situation for principalagent delegation when used as a target. We also show several new dual results such as utility dominance relationships as dual to stochastic dominance relationships and introduce a new saddlepoint method for allocating lotteries to decision makers. Key words: utility, probability, duality, aspiration equivalent, and utility dominance. Page 1 © 2003 Utility Probability Duality 102703.doc 1 – Introduction to duality
Bayesian Networks with Degenerate Gaussian Distributions
 Methodology and Computing in Applied Probability
, 2001
"... Bayesian networks compute marginal distributions through the "message passing" algorithm  a series of local calculations involving neighboring cliques of variables in a clique tree. In this work, these message passing computations are extended to the case of degenerate Gaussian potentials which a ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Bayesian networks compute marginal distributions through the "message passing" algorithm  a series of local calculations involving neighboring cliques of variables in a clique tree. In this work, these message passing computations are extended to the case of degenerate Gaussian potentials which are multivariate Gaussian densities that can have two different kinds of degeneracies corresponding to projections with zero variance and projections with infinite variance. The basic operations of the message passing algorithm, such as representing conditional distributions, extending potentials, and conditioning on observations, create or operate on potentials with various kinds of degeneracies thereby demonstrating the need for such methodology. Computer implementation of this scheme follows easily from the details within and some computational aspects are discussed. We also demonstrate an application of our methodology to automatic musical accompaniment.
Three new sensitivity analysis methods for influence diagrams
 In Proc. of 26th UAI
, 2010
"... Performing sensitivity analysis for influence diagrams using the decision circuit framework is particularly convenient, since the partial derivatives with respect to every parameter are readily available [Bhattacharjya and Shachter, 2007; 2008]. In this paper we present three nonlinear sensitivity ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Performing sensitivity analysis for influence diagrams using the decision circuit framework is particularly convenient, since the partial derivatives with respect to every parameter are readily available [Bhattacharjya and Shachter, 2007; 2008]. In this paper we present three nonlinear sensitivity analysis methods that utilize this partial derivative information and therefore do not require reevaluating the decision situation multiple times. Specifically, we show how to efficiently compare strategies in decision situations, perform sensitivity to risk aversion and compute the value of perfect hedging [Seyller, 2008]. 1