Peter Haddawy

AIIM Journal 2025 Journal Article

SDMentor: A virtual reality-based intelligent tutoring system for surgical decision making in dentistry

• Narumol Vannaprathip
• Peter Haddawy
• Holger Schultheis
• Siriwan Suebnukarn

Background While VR simulation has already had a significant impact on training of psychomotor surgical skills, there is still a lack of work on the use of VR simulation to teach surgical decision making. Since surgical decision making is a cognitive process, a simulation for teaching it must be able to not only accurately simulate the surgical environment but to also represent and reason about the cognitive aspects involved. Materials and methods This paper presents and evaluates SDMentor, a virtual training environment that integrates high-fidelity VR simulation with an intelligent tutoring system for teaching surgical decision making in dentistry. SDMentor provides a virtual dental operating room with 3D stereoscopic graphics and with haptic feedback to realistically render the interaction of dental tools with the patient teeth. The intelligent tutor evaluates the student's actions and generates a variety of tutorial feedback. To evaluate the teaching effectiveness of the system, we carried out a randomized controlled trial in the domain of root canal treatment. Results In all three aspects of scores: situation awareness ability, procedural knowledge, and overall performance; the post-test scores showed significant improvement over the pre-test scores of students in the same group (P <. 05). The students from the experimental group had significantly higher learning gains than the students in the control group (P <. 05). Conclusions The integration of high-fidelity VR simulation with intelligent tutoring is a promising approach to teaching surgical decision making and could be useful for teaching decision making in other high-precision psychomotor tasks.

AIIM Journal 2023 Journal Article

Quantifying the impact of data characteristics on the transferability of sleep stage scoring models

• Akara Supratak
• Peter Haddawy

Deep learning models for scoring sleep stages based on single-channel EEG have been proposed as a promising method for remote sleep monitoring. However, applying these models to new datasets, particularly from wearable devices, raises two questions. First, when annotations on a target dataset are unavailable, which different data characteristics affect the sleep stage scoring performance the most and by how much? Second, when annotations are available, which dataset should be used as the source of transfer learning to optimize performance? In this paper, we propose a novel method for computationally quantifying the impact of different data characteristics on the transferability of deep learning models. Quantification is accomplished by training and evaluating two models with significant architectural differences, TinySleepNet and U-Time, under various transfer configurations in which the source and target datasets have different recording channels, recording environments, and subject conditions. For the first question, the environment had the highest impact on sleep stage scoring performance, with performance degrading by over 14% when sleep annotations were unavailable. For the second question, the most useful transfer sources for TinySleepNet and the U-Time models were MASS-SS1 and ISRUC-SG1, containing a high percentage of N1 (the rarest sleep stage) relative to the others. The frontal and central EEGs were preferred for TinySleepNet. The proposed approach enables full utilization of existing sleep datasets for training and planning model transfer to maximize the sleep stage scoring performance on a target problem when sleep annotations are limited or unavailable, supporting the realization of remote sleep monitoring.

AIIM Journal 2018 Journal Article

Spatiotemporal Bayesian networks for malaria prediction

• Peter Haddawy
• A.H.M. Imrul Hasan
• Rangwan Kasantikul
• Saranath Lawpoolsri
• Patiwat Sa-angchai
• Jaranit Kaewkungwal
• Pratap Singhasivanon

Targeted intervention and resource allocation are essential for effective malaria control, particularly in remote areas, with predictive models providing important information for decision making. While a diversity of modeling technique have been used to create predictive models of malaria, no work has made use of Bayesian networks. Bayes nets are attractive due to their ability to represent uncertainty, model time lagged and nonlinear relations, and provide explanations. This paper explores the use of Bayesian networks to model malaria, demonstrating the approach by creating village level models with weekly temporal resolution for Tha Song Yang district in northern Thailand. The networks are learned using data on cases and environmental covariates. Three types of networks are explored: networks for numeric prediction, networks for outbreak prediction, and networks that incorporate spatial autocorrelation. Evaluation of the numeric prediction network shows that the Bayes net has prediction accuracy in terms of mean absolute error of about 1. 4 cases for 1 week prediction and 1. 7 cases for 6 week prediction. The network for outbreak prediction has an ROC AUC above 0. 9 for all prediction horizons. Comparison of prediction accuracy of both Bayes nets against several traditional modeling approaches shows the Bayes nets to outperform the other models for longer time horizon prediction of high incidence transmission. To model spread of malaria over space, we elaborate the models with links between the village networks. This results in some very large models which would be far too laborious to build by hand. So we represent the models as collections of probability logic rules and automatically generate the networks. Evaluation of the models shows that the autocorrelation links significantly improve prediction accuracy for some villages in regions of high incidence. We conclude that spatiotemporal Bayesian networks are a highly promising modeling alternative for prediction of malaria and other vector-borne diseases.

ECAI Conference 2016 Conference Paper

Integrating ARIMA and Spatiotemporal Bayesian Networks for High Resolution Malaria Prediction

• A. H. M. Imrul Hasan
• Peter Haddawy

Since malaria is prevalent in less developed and more remote areas in which public health resources are often scarce, targeted intervention is essential in allocating resources for effective malaria control. To effectively support targeted intervention, predictive models must be not only accurate but they must also have high temporal and spatial resolution to help determine when and where to intervene. In this paper we take the first essential step towards a system to support targeted intervention in Thailand by developing a high resolution prediction model through the combination of Bayes nets and ARIMA. Bayes nets and ARIMA have complementary strengths, with the Bayes nets better able to represent the effect of environmental variables and ARIMA better able to capture the characteristics of the time series of malaria cases. Leveraging these complementary strengths, we develop an ensemble predictor from the two that has significantly better accuracy that either predictor alone. We build and test the models with data from Tha Song Yang district in northern Thailand, creating village-level models with weekly temporal resolution.

AIIM Journal 2011 Journal Article

Intelligent dental training simulator with objective skill assessment and feedback

• Phattanapon Rhienmora
• Peter Haddawy
• Siriwan Suebnukarn
• Matthew N. Dailey

Objective We present a dental training simulator that provides a virtual reality (VR) environment with haptic feedback for dental students to practice dental surgical skills in the context of a crown preparation procedure. The simulator addresses challenges in traditional training such as the subjective nature of surgical skill assessment and the limited availability of expert supervision. Methods and materials We identified important features for characterizing the quality of a procedure based on interviews with experienced dentists. The features are patterns combining tool position, tool orientation, and applied force. The simulator monitors these features during the procedure, objectively assesses the quality of the performed procedure using hidden Markov models (HMMs), and provides objective feedback on the user's performance in each stage of the procedure. We recruited five dental students and five experienced dentists to evaluate the accuracy of our skill assessment method and the quality of the system's generated feedback. Results The experimental results show that HMMs with selected features can correctly classify all test sequences into novice and expert categories. The evaluation also indicates a high acceptance rate from experts for the system's generated feedback. Conclusion In this work, we introduce our VR dental training simulator and describe a mechanism for providing objective skill assessment and feedback. The HMM is demonstrated as an effective tool for classifying a particular operator as novice-level or expert-level. The simulator can generate tutoring feedback with quality comparable to the feedback provided by human tutors.

AIIM Journal 2007 Journal Article

Anatomical sketch understanding: Recognizing explicit and implicit structure

• Peter Haddawy
• Matthew N. Dailey
• Ploen Kaewruen
• Natapope Sarakhette
• Le Hong Hai

Objective Sketching is ubiquitous in medicine. Physicians commonly use sketches as part of their note taking in patient records and to help convey diagnoses and treatments to patients. Medical students frequently use sketches to help them think through clinical problems in individual and group problem solving. Applications ranging from automated patient records to medical education software could benefit greatly from the richer and more natural interfaces that would be enabled by the ability to understand sketches. In this paper we take the first steps toward developing a system that can understand anatomical sketches. Methods Understanding an anatomical sketch requires the ability to recognize what anatomical structure has been sketched and from what view (e. g. parietal view of the brain), as well as to identify the anatomical parts and their locations in the sketch (e. g. parts of the brain), even if they have not been explicitly drawn. We present novel algorithms for sketch recognition and for part identification. We evaluate the accuracy of the recognition algorithm on sketches obtained from medical students. We evaluate the part identification algorithm by comparing its results to the judgment of an experienced physician. Results The sketch recognition algorithm achieves a recognition accuracy of 75. 5%, far above the baseline random classification accuracy of 6. 7%. Comparison of the results of the part identification algorithm with the judgment of an experienced physician shows close agreement in terms of location, orientation, size, and shape of the identified parts. Conclusions The performance of our prototype in terms of accuracy and running time provides strong evidence that development of robust sketch understanding systems for medical domains is an attainable goal. Further work needs to be done to extend the approach to sketches containing multiple and partial anatomical structures, as well as to be able to interpret sketch annotations.

IS Journal 2007 Journal Article

COMET: A Collaborative Tutoring System for Medical Problem-Based Learning

• Siriwan Suebnukarn
• Peter Haddawy

This paper discussed about the developed collaborative intelligent tutoring system for medical PBL called Comet (collaborative medical tutor). Comet uses Bayesian networks to model the knowledge and activity of individual students as well as small groups. It applies generic tutoring algorithms to these models and generates tutorial hints that guide problem solving. An early laboratory study shows a high degree of agreement between the hints generated by Comet and those of experienced human tutors. Evaluations of Comet's clinical-reasoning model and the group reasoning path provide encouraging support for the general framework.

AIIM Journal 2006 Journal Article

A Bayesian approach to generating tutorial hints in a collaborative medical problem-based learning system

• Siriwan Suebnukarn
• Peter Haddawy

Objectives Today a great many medical schools have turned to a problem-based learning (PBL) approach to teaching. While PBL has many strengths, effective PBL requires the tutor to provide a high degree of personal attention to the students, which is difficult in the current academic environment of increasing demands on faculty time. This paper describes intelligent tutoring in a collaborative medical tutor for PBL. The main contribution of our work is the development of representational techniques and algorithms for generating tutoring hints in PBL group problem solving, as well as the implementation of these techniques in a collaborative intelligent tutoring system, COMET. The system combines concepts from computer-supported collaborative learning with those from intelligent tutoring systems. Methods and materials The system uses Bayesian networks to model individual student clinical reasoning, as well as that of the group. The prototype system incorporates substantial domain knowledge in the areas of head injury, stroke and heart attack. Tutoring in PBL is particularly challenging since the tutor should provide as little guidance as possible while at the same time not allowing the students to get lost. From studies of PBL sessions at a local medical school, we have identified and implemented eight commonly used hinting strategies. In order to evaluate the appropriateness and quality of the hints generated by our system, we compared the tutoring hints generated by COMET with those of experienced human tutors. We also compared the focus of group activity chosen by COMET with that chosen by human tutors. Results On average, 74. 17% of the human tutors used the same hint as COMET. The most similar human tutor agreed with COMET 83% of the time and the least similar tutor agreed 62% of the time. Our results show that COMET's hints agree with the hints of the majority of the human tutors with a high degree of statistical agreement (McNemar test, p =0. 652, κ =0. 773). The focus of group activity chosen by COMET agrees with that chosen by the majority of the human tutors with a high degree of statistical agreement (McNemar test, p =0. 774, κ =0. 823). Conclusion Bayesian network clinical reasoning models can be combined with generic tutoring strategies to successfully emulate human tutor hints in group medical PBL.

IJCAI Conference 2003 Conference Paper

Constructing utility models from observed negotiation actions

• Angelo Restijicar
• Peter Haddawy

We propose a novel method for constructing utility models by learning from observed negotiation actions. In particular, we show how offers and counter-offers in negotiation can be transformed into gamble questions providing the basis for eliciting utility functions. Results of experiments and evaluation are briefly described.

JMLR Journal 2003 Journal Article

Preference Elicitation via Theory Refinement

• Peter Haddawy
• Vu Ha
• Angelo Restificar
• Benjamin Geisler
• John Miyamoto

We present an approach to elicitation of user preference models in which assumptions can be used to guide but not constrain the elicitation process. We demonstrate that when domain knowledge is available, even in the form of weak and somewhat inaccurate assumptions, significantly less data is required to build an accurate model of user preferences than when no domain knowledge is provided. This approach is based on the KBANN (Knowledge-Based Artificial Neural Network) algorithm pioneered by Shavlik and Towell (1989). We demonstrate this approach through two examples, one involves preferences under certainty, and the other involves preferences under uncertainty. In the case of certainty, we show how to encode assumptions concerning preferential independence and monotonicity in a KBANN network, which can be trained using a variety of preferential information including simple binary classification. In the case of uncertainty, we show how to construct a KBANN network that encodes certain types of dominance relations and attitude toward risk. The resulting network can be trained using answers to standard gamble questions and can be used as an approximate representation of a person's preferences. We empirically evaluate our claims by comparing the KBANN networks with simple backpropagation artificial neural networks in terms of learning rate and accuracy. For the case of uncertainty, the answers to standard gamble questions used in the experiment are taken from an actual medical data set first used by Miyamoto and Eraker (1988). In the case of certainty, we define a measure to which a set of preferences violate a domain theory, and examine the robustness of the KBANN network as this measure of domain theory violation varies. [abs] [ pdf ][ ps.gz ][ ps ]

AIJ Journal 2003 Journal Article

Similarity of personal preferences: Theoretical foundations and empirical analysis

• Vu Ha
• Peter Haddawy

We study the problem of defining similarity measures on preferences from a decision-theoretic point of view. We propose a similarity measure, called probabilistic distance, that originates from the Kendall's tau function, a well-known concept in the statistical literature. We compare this measure to other existing similarity measures on preferences. The key advantage of this measure is its extensibility to accommodate partial preferences and uncertainty. We develop efficient methods to compute this measure, exactly or approximately, under all circumstances. These methods make use of recent advances in the area of Markov chain Monte Carlo simulation. We discuss two applications of the probabilistic distance: in the construction of the Decision-Theoretic Video Advisor (diva), and in robustness analysis of a theory refinement technique for preference elicitation.

UAI Conference 2001 Conference Paper

Similarity Measures on Preference Structures, Part II: Utility Functions

• Vu A. Ha
• Peter Haddawy
• John Miyamoto

UAI Conference 1999 Conference Paper

A Hybrid Approach to Reasoning with Partially Elicited Preference Models

• Vu A. Ha
• Peter Haddawy

Classical Decision Theory provides a normative framework for representing and reasoning about complex preferences. Straightforward application of this theory to automate decision making is difficult due to high elicitation cost. In response to this problem, researchers have recently developed a number of qualitative, logic-oriented approaches for representing and reasoning about references. While effectively addressing some expressiveness issues, these logics have not proven powerful enough for building practical automated decision making systems. In this paper we present a hybrid approach to preference elicitation and decision making that is grounded in classical multi-attribute utility theory, but can make effective use of the expressive power of qualitative approaches. Specifically, assuming a partially specified multilinear utility function, we show how comparative statements about classes of decision alternatives can be used to further constrain the utility function and thus identify sup-optimal alternatives. This work demonstrates that quantitative and qualitative approaches can be synergistically integrated to provide effective and flexible decision support.

UAI Conference 1999 Conference Paper

The Decision-Theoretic Interactive Video Advisor

• Hien Nguyen
• Peter Haddawy

The need to help people choose among large numbers of items and to filter through large amounts of information has led to a flood of research in construction of personal recommendation agents. One of the central issues in constructing such agents is the representation and elicitation of user preferences or interests. This topic has long been studied in Decision Theory, but surprisingly little work in the area of recommender systems has made use of formal decision-theoretic techniques. This paper describes DIVA, a decision-theoretic agent for recommending movies that contains a number of novel features. DIVA represents user preferences using pairwise comparisons among items, rather than numeric ratings. It uses a novel similarity measure based on the concept of the probability of conflict between two orderings of items. The system has a rich representation of preference, distinguishing between a user's general taste in movies and his immediate interests. It takes an incremental approach to preference elicitation in which the user can provide feedback if not satisfied with the recommendation list. We empirically evaluate the performance of the system using the EachMovie collaborative filtering database.

ICAPS Conference 1998 Conference Paper

A Modular Structured Approach to Conditional Decision-Theoretic Planning

• Liem Ngo
• Peter Haddawy
• Hien Nguyen

A realistic systemfor planningwith unccrtaln information in partially observable domainsmust be able to reason about sensing actions and to condition its further actions on the sensed information. Amongimplemented planning systems, we can distinguish two approaches to contingent decision-theoretic planning. The first is characterized by a highly unconstrained plan space, while the secondis characterized by a constrained and inflexible specification of plan space. In this paper, we take a middle ground between these two approachesthat we consider to be more practical. Weperm/tttLe nser to specie" the. structure of the space of possible plans to bc consideredbut to do so in a flexible manner. This flexibility is obtained through the use of a modularrepresentation. VV~separate the representation of actions from the representation of domainrelations and we separate those from the representation of the plan space. Acti, ms and domainrelations are represented with schematic Ba~s net fragments and plan space is represented using programming language constructs. Wepresent a planning system that can find optimal plans given this rcpresentation.

UAI Conference 1998 Conference Paper

Toward Case-Based Preference Elicitation: Similarity Measures on Preference Structures

• Vu A. Ha
• Peter Haddawy

While decision theory provides an appealing normative framework for representing rich preference structures, eliciting utility or value functions typically incurs a large cost. For many applications involving interactive systems this overhead precludes the use of formal decision-theoretic models of preference. Instead of performing elicitation in a vacuum, it would be useful if we could augment directly elicited preferences with some appropriate default information. In this paper we propose a case-based approach to alleviating the preference elicitation bottleneck. Assuming the existence of a population of users from whom we have elicited complete or incomplete preference structures, we propose eliciting the preferences of a new user interactively and incrementally, using the closest existing preference structures as potential defaults. Since a notion of closeness demands a measure of distance among preference structures, this paper takes the first step of studying various distance measures over fully and partially specified preference structures. We explore the use of Euclidean distance, Spearmans footrule, and define a new measure, the probabilistic distance. We provide computational techniques for all three measures.

TCS Journal 1997 Journal Article

Answering queries from context-sensitive probabilistic knowledge bases

• Liem Ngo
• Peter Haddawy

We define a language for representing context-sensitive probabilistic knowledge. A knowledge base consists of a set of universally quantified probability sentences that include context constraints, which allow inference to be focused on only the relevant portions of the probabilistic knowledge. We provide a declarative semantics for our language. We present a query answering procedure that takes a query Q and a set of evidence E and constructs a Bayesian network to compute P(Q¦E). The posterior probability is then computed using any of a number of Bayesian network inference algorithms. We use the declarative semantics to prove the query procedure sound and complete. We use concepts from logic programming to justify our approach.

AIIM Journal 1997 Journal Article

BANTER: a Bayesian network tutoring shell

• Peter Haddawy
• Joel Jacobson
• Charles E Kahn

We present an educational tool for bringing the information contained in a Bayesian network to the end user in an easily intelligible form. The banter shell is designed to tutor users in evaluation of hypotheses and selection of optimal diagnostic procedures. banter can be used with any Bayesian network containing nodes that can be classified into hypotheses, observations, and diagnostic procedures. The system enables one to present various types of queries to the network, to test one's ablity to select optimal diagnostic procedures, and to request explanations. We describe the system's capabilities by illustrating how it functions with two structurally different network models of real-world medical problems.

UAI Conference 1997 Conference Paper

Problem-Focused Incremental Elicitation of Multi-Attribute Utility Models

• Vu A. Ha
• Peter Haddawy

AIJ Journal 1996 Journal Article

A logic of time, chance, and action for representing plans

• Peter Haddawy

This paper integrates logical and probabilistic approaches to the representation of planning problems by developing a first-order logic of time, chance, and action. We start by making explicit and precise commonsense notions about time, chance, and action central to the planning problem. We then develop a logic, the semantics of which incorporates these intuitive properties. The logical language integrates both modal and probabilistic constructs and allows quantification over time points, probability values, and domain individuals. Probability is treated as a sentential operator in the language, so it can be arbitrarily nested and combined with other logical operators. The language can represent the chance that facts hold and events occur at various times. It can represent the chance that actions and other events affect the future. The model of action distinguishes between action feasibility, executability, and effects. We present a proof theory for the logic and show how the logic can be used to describe actions in such a way that the action descriptions can be composed to infer properties of plans via the proof theory.

UAI Conference 1996 Conference Paper

Sound Abstraction of Probabilistic Actions in The Constraint Mass Assignment Framework

• AnHai Doan
• Peter Haddawy

This paper provides a formal and practical framework for sound abstraction of probabilistic actions. We start by precisely defining the concept of sound abstraction within the context of finite-horizon planning (where each plan is a finite sequence of actions). Next we show that such abstraction cannot be performed within the traditional probabilistic action representation, which models a world with a single probability distribution over the state space. We then present the constraint mass assignment representation, which models the world with a set of probability distributions and is a generalization of mass assignment representations. Within this framework, we present sound abstraction procedures for three types of action abstraction. We end the paper with discussions and related work on sound and approximate abstraction. We give pointers to papers in which we discuss other sound abstraction-related issues, including applications, estimating loss due to abstraction, and automatically generating abstraction hierarchies.

UAI Conference 1996 Conference Paper

Theoretical Foundations for Abstraction-Based Probabilistic Planning

• Vu A. Ha
• Peter Haddawy

UAI Conference 1995 Conference Paper

A Theoretical Framework for Context-Sensitive Temporal Probability Model Construction with Application to Plan Projection

• Liem Ngo
• Peter Haddawy
• James Helwig

UAI Conference 1995 Conference Paper

Efficient Decision-Theoretic Planning: Techniques and Empirical Analysis

• Peter Haddawy
• AnHai Doan
• Richard Goodwin

This paper discusses techniques for performing efficient decision-theoretic planning. We give an overview of the DRIPS decision-theoretic refinement planning system, which uses abstraction to efficiently identify optimal plans. We present techniques for automatically generating search control information, which can significantly improve the planner's performance. We evaluate the efficiency of DRIPS both with and without the search control rules on a complex medical planning problem and compare its performance to that of a branch-and-bound decision tree algorithm.

UAI Conference 1994 Conference Paper

Abstracting Probabilistic Actions

• Peter Haddawy
• AnHai Doan

This paper discusses the problem of abstracting conditional probabilistic actions. We identify two distinct types of abstraction: intra-action abstraction and inter-action abstraction. We define what it means for the abstraction of an action to be correct and then derive two methods of intra-action abstraction and two methods of inter-action abstraction which are correct according to this criterion. We illustrate the developed techniques by applying them to actions described with the temporal action representation used in the DRIPS decision-theoretic planner and we describe how the planner uses abstraction to reduce the complexity of planning.

AIJ Journal 1994 Journal Article

Anytime deduction for probabilistic logic

• Alan M. Frisch
• Peter Haddawy

This paper proposes and investigates an approach to deduction in probabilistic logic, using as its medium a language that generalizes the propositional version of Nilsson's probabilistic logic by incorporating conditional probabilities. Unlike many other approaches to deduction in probabilistic logic, this approach is based on inference rules and therefore can produce proofs to explain how conclusions are drawn. We show how these rules can be incorporated into an anytime deduction procedure that proceeds by computing increasingly narrow probability intervals that contain the tightest entailed probability interval. Since the procedure can be stopped at any time to yield partial information concerning the probability range of any entailed sentence, one can make a tradeoff between precision and computation time. The deduction method presented here contrasts with other methods whose ability to perform logical reasoning is either limited or requires finding all truth assignments consistent with the given sentences.

TIME Conference 1994 Conference Paper

Believing Change and Changing Belief

• Peter Haddawy

We present a first-order logic of time, chance, and probability that is capable of expressing the four types of higher-order probability sentences relating subjective probability and objective chance at different times. We define a causal notion of objective chance and show how it can be used in conjunction with subjective probability to distinguish between causal and evidential correlation by distinguishing between conditions, events, and actions that 1) influence the agent's belief in chance and 2) the agent believes to influence chance. Furthermore, the semantics of the logic captures some commonsense inferences concerning objective chance and causality. We show that an agent's subjective probability is the expected value of its beliefs concerning objective chance. We also prove that an agent using this representation believes with certainty that the past cannot be causally influenced.

ICAPS Conference 1994 Conference Paper

Decision-theoretic Refinement Planning Using Inheritance Abstraction

• Peter Haddawy
• Meliani Suwandi

plan’s outcomes are sets of outcomes of more those that might be refinable to the optimal plan. The concrete plans. Since different probability and utility values mav be associated with each specific outcome.. in general a probability range and a utility range will be associated with each abstract outcome. Thus the expected utility of an abstract plan is represented by an interval, which includes the expected utilities of all possible instantiations of that abstract plan. Refining the plan, i. e., instantiating one of its actions, tends to narrow the interval. Whenthe expected utility intervals of two plans do not overlap, the one with the lower 1intcrval can be eliminated. Wepresent a method for abstracting probabilistic conditional actions and we show how to compute expected utility bounds for plans containing such abstract actions. Wepresent a planning algorithm that *This work was inspired by discussions with Steve Hanks. Manonton Butaxbutar performed the complexity analysis of the algorithm. This work was partially supported by NSFgrant #IRI-9207262. 1If the upper boundon the expected utility of each abstract plan is tight, i. e., there is an instanceof the abstract plan with that expected utility, then at each refinement step we can eliminate all abstract plans but the one with the highest upper bound. 266 POSTERS From: AIPS 1994 Proceedings. Copyright © 1994, AAAI (www. aaai. org). All deli sati i live func degr pone DSAf comp temp 0 2 tons 85 155time the of a UR bini DSAa dead rese a go that over resi F 2. 5 4. 5 fed ourt from Figure 2: Specification of delivery utility function. woul tons bene

UAI Conference 1994 Conference Paper

Generating Bayesian Networks from Probablity Logic Knowledge Bases

• Peter Haddawy

KER Journal 1990 Journal Article

Planning and decision theory

• Peter Haddawy
• Larry Rendell

Research on planning in AI can be separated into the two major areas: plan generation and plan representation. Most AI planners to date have been based on the STRIPS planning representation. This representation has a number of limitations. Much recent work in plan representation has addressed these limitations. It was shown that Decision Theory can be used to remove a number of the limitations. Furthermore, the decision theoretic framework provides a precise definition of rational behaviour. There remain open questions within decision theory regarding belief revision and causality. It should be noted that these problems are not artifacts of the representation. Rather they arise because the rich representation allows their formulation. Some work integrating AI and decision theoretic approaches to planning has been done but this remains a largely untouched research area. We see two main avenues for fruitful research. First, the straightforward decision theoretic formulation of planning is computationally impractical. Techniques need to be developed to do efficient decision theoretic planning. Work in AI plan generation has exploited information contained the structure of qualitative representations to guide efficient plan construction. These techniques should be applied to decision theoretic representations as well. Second, AI has developed many representations that allow useful structuring of knowledge about the world. Decision Theory has concentrated on representing beliefs and desires. Integration of AI and decision theoretic representations would yield powerful representation languages. Some of the benefits of such work can already be seen in the research combining temporal and decision theoretic representations.

UAI Conference 1990 Conference Paper

Time, chance and action

• Peter Haddawy

UAI Conference 1988 Conference Paper

Modal logics of higher-order probability

• Peter Haddawy
• Alan M. Frisch

AAAI Conference 1986 Conference Paper

Implementation of and Experiments with a Variable Precision Logic Inference System

• Peter Haddawy

A system capable of performing approximate inferences under time constraints is presented. Censored production rules are used to represent both domain and control information. These are given a probabilistic semantics and reasoning is performed using a scheme based on Dempster-Shafer theory. Examples show the naturalness of the representation and the flexibility of the system. Suggestions for further research are offered.