This directory is created automatically and some papers may be mislabeled. Only document within the CiteSeer database are listed. The directory is intended to provide entry points for browsing the database and is not intended to be authoritative. Papers may not appear in all relevant categories. For example, papers in a sub-category may not appear in higher level categories.
Learning DFA from Simple Examples - Parekh, Honavar (2001)(Correct)
Efficient learning of DFA is a challenging research problem in grammatical inference. It is known that both exact and approximate (in the PAC sense) identifiability of DFA is hard. Pitt, in his semina... / Allstate Research and Planning Center Middlefield Road br Learning DFA from Simple Examples
Case-Base Maintenance: The Husbandry of Experience - Wilson (2001)(Correct)
Case-based reasoning (CBR) is an artificial intelligence methodology that uses specific encapsulated prior experiences as a basis for reasoning about similar new situations. CBR systems rely on variou... / in the CHEF system for recipe planning Hammond if the current br Lenz et al. for planning tasks such as design and
An Indexed Bibliography of Genetic Algorithms and Neural Networks - Jarmo T. Alander (2001)(Correct)
s: July 1996 - Nov. 1997
ffl ChA: Chemical Abstracts: Jan. 1997 - Aug. 1998
ffl CA: Computer Abstracts: Jan. 1993 -- Feb. 1995
ffl CCA: Computer & Control Abstracts: Jan. 1992 -- Apr. 1998 (except ... / help to those who are working or planning to work in this rapidly growing br patent path planning pattern recognition
Parts Feeding on a Conveyor with a One Joint Robot - Akella, Huang, Lynch, Mason (2000)(Correct)
This paper explores a method of manipulating a planar rigid part on a conveyor belt using a
robot with just one joint. This approach has the potential of offering a simple and flexible method for fe... / polygonal parts. We present the planners for these systems and describe br Robotics Manipulation Mechanics Planning Minimalism Automation
Active object recognition by view integration and reinforcement.. - Paletta, Pinz (2000)(Correct)
A mobile agent with the task to classify its sensor pattern has to cope with ambiguous information. Active recognition of
three-dimensional objects involves the observer in a search for discriminative... / Information fusion Viewpoint planning . Introduction Autonomous br explicit reasoning for viewpoint planning The reinforcement
Identifying Qualitatively Different Experiences: Experiments with a.. - Oates, Schmill, Cohen (2000)(Correct)
We present an unsupervised learning method
that allows a situated embodied agent to identify
and represent qualitatively different experiences.
The occurrence of events, such as the
initiation of a pa... / can be used for off-line planning and for on-line prediction by br change. For example planning requires knowledge of how actions
Object-Oriented Design Of Automated Highway Simulations Using Shift.. - Göllü, Kourjanski (2000)(Correct)
SmartAHS is a specification, simulation, and evaluation framework for modeling, control and
evaluation of Automated Highway Systems (AHS). SmartAHS is developed using SHIFT, a new
programming language... / Automated Highway System AHS Planning an Automated Highway System is a br learning and trajectory planning in the face of diverse threats
Constructive Neural Network Learning Algorithms for Pattern.. - Parekh, Yang, Honavar (2000)(Correct)
Constructive learning algorithms offer an attractive
approach for the incremental construction of near-minimal
neural-network architectures for pattern classification. They help
overcome the need for ... / is with Allstate Research and Planning Center Menlo Park CA USA br at the Allstate Research and Planning Center Menlo Park CA. His
An Indexed Bibliography of Genetic Algorithms in Japan - Jarmo T. Alander (2000)(Correct)
s: Jan. 1995 { Sep. 1998
ACM: ACM Guide to Computing Literature: 1979 - 1993/4
BA: Biological Abstracts: July 1996 - Aug. 1998
CA: Computer Abstracts: Jan. 1993 { Feb. 1995
CCA: Computer &... / cation rule based systems planning arti cial life system br help to those who are working or planning to work in this rapidly growing
Evolving Artificial Neural Networks - Yao (1999)(Correct)
Learning and evolution are two fundamental forms of adaptation. There has been a great
interest in combining learning and evolution with artificial neural networks (ANNs) in recent
years. This paper (... / neural network for robot path planning in Proceedings of the br N. Noguchi and H. Terao Path planning of an agricultural mobile robot
Experiences with an Interactive Museum Tour-Guide Robot - Burgard, Cremers, Fox, Hähnel.. (1999)(Correct)
This article describes the software architecture of an autonomous, interactive tour-guide
robot. It presents a modular and distributed software architecture, which integrates localization,
mapping, co... / mapping collision avoidance planning and various modules concerned br reasoning localization mapping planning collision avoidance logic
Background to Qualitative Decision Theory - Doyle, Thomason (1999)(Correct)
This paper provides an overview of the field of qualitative
decision theory: its motivating tasks and issues, its
antecedents, and its prospects. Qualitative decision theory
studies qualitative approa... / . Decision-theoretic planning . br . . Sympathetic planning .
Schmidhuber's lab - Turteltaub (1999)(Correct)
A preliminary attempt at collecting references to the work of Jurgen Schmidhuber and his
machine learning research group.
Overview
In the final decade of this millenium Schmidhuber has produced wel... / dynamic reinforcement learning and planning in non-stationary environments. br Schmidhuber and his machine learning research group. Overview In
Modeling Human-Body Soft Tissues for Surgical Applications - Latombe (1999)(Correct)
irtual characters.
Previous research on soft-tissue modeling provides foundations on which the proposed research is
based. In particular, as several researchers have suggested before, tissue structure... / in graphics vision and motion planning . br for diagnosis and surgical planning. Combined with advances of
Rational Coordination in Multi-Agent Environments - Gmytrasiewicz, Durfee (1999)(Correct)
We adopt the decision-theoretic principle of expected utility maximization as a
paradigm for designing autonomous rational agents, and present a framework that uses
this paradigm to determine the ch... / routines that update the KB planning routines that propose br posed by learning sensing and planning we concentrate solely on the
User interface affordances in a planning representation - Amant (1999)(Correct)
This article shows how the concept of affordance in the user interface fits into a wellunderstood
artificial intelligence (AI) model of acting in an environment. In this model AI
planning research is ... / User interface affordances in a planning representation Robert St. br University. Affordances in a planning representation Abstract
Learning Action Strategies for Planning Domains - Khardon (1999)(Correct)
This paper reports on experiments where techniques of supervised machine learning are
applied to the problem of planning. The input to the learning algorithm is composed
of a description of a planning... / Learning Action Strategies for Planning Domains Roni Khardon br are applied to the problem of planning. The input to the learning
Generalization and Generalizability Measures - Wah (1999)(Correct)
In this paper, we define the generalization problem, summarize various
approaches in generalization, identify the credit assignment problem,
and present the problem and some solutions in measuring gen... / Space Rule Space Experiment Planning Instance Selection Result br rule space and involves experiment planning instance selection and result
Self-Organizing Maps for Pattern Classification - Atukorale (1999)(Correct)
We are investigating novel architectures of self-organizing maps for pattern classification
tasks. We started our research by investigating a recently proposed algorithm
known as the neural gas (NG) a... / for combining classifiers. We are planning to interpret their outputs as br classifiers for combining. We are planning to interpret their outputs as
Learning Situation-Specific Coordination in Cooperative Multi-agent.. - Prasad, Lesser (1999)(Correct)
Achieving effective cooperation in a multi-agent system is a difficult problem for a number of
reasons such as limited and possiblyout-dated views of activities of other agents and uncertainty
about t... / called Generalized Partial Global Planning GPGP GPGP is a flexible br in Generalized Partial Global Planning. In AAAI Spring Symposium
An Overview of Some Recent Developments in Bayesian Problem Solving.. - Haddaway (1999)(Correct)
The last five years have seen a surge in interest in the use of techniques from Bayesian decision theory to
address problems in AI. Decision theory provides a normative framework for representing and ... / networks decision-theoretic planning and qualitative decision theory. br processing robot navigation planning and machine learning. One sign
Semantic Query Optimization for Query Plans of Heterogeneous.. - Hsu, Knoblock (1999)(Correct)
New applications of information systems, such as electronic commerce and healthcare information
systems, need to integrate a large number of heterogeneous databases over computer
networks. Answering a... / about intermediate data at query planning time. To address this issue br have proposed interleaving query planning and execution so that the query
Toward a Morphosyntactic User Model for Language Analysis and.. - Michaud (1999)(Correct)
This proposal paper is being presented in partial fulfillment of the Ph.D. requirements of the Department
of Computer and Information Sciences at the University of Delaware. In this paper, I discuss a... / Text Generation in ICICLE . Planner Overview . br a Multi-Phasic Text Planner .
Functional Strips: a more general language for planning and problem.. - Bonet, Geffner (1999)(Correct)
The Strips language introduced by Fikes and Nilsson in 1971 has
shaped most of the work in Planning. Its appeal can be explained by
two reasons: Strips provides a compact language for representing act... / a more general language for planning and problem solving Preliminary br has shaped most of the work in Planning. Its appeal can be explained by
A Survey of Agent-Oriented Methodologies - Iglesias, Garijo, Gonzalez (1999)(Correct)
This article introduces the current agent-oriented methodologies. It discusseswhat approacheshave been followed (mainly extending existing objectoriented and knowledge engineering methodologies), th... / carry out their inferences their planning process etc. Finally agents br actuators world knowledge and planning abilities. Then a suitable agent
The LPSAT Engine & its Application to Resource Planning - Wolfman, Weld (1999)(Correct)
Compilation to boolean satisfiability has become a powerful paradigm for solving AI problems. However, domains that require metric reasoning cannot be compiled efficiently to SAT even if they would ot... / its Application to Resource Planning y Steven A. Wolfman Daniel br which converts metric resource planning problems into lcnf for
ADORE: Adaptive Object Recognition - Draper, Bins, Baek (1999)(Correct)
Many modern computer vision systems are built by chaining
together standard vision procedures, often in graphical programming
environments such as Khoros, CVIPtools or IUE. Typically, these procedur... / have applied AI-style planning technology to infer control br C. Ying and S. Hsiao. Integrated Planning for Automated Image Processing
Case-Based Reasoning - Survey and Future Directions - Bartsch-Spörl, Lenz, Hübner (1999)(Correct)
This paper surveys the field of case-based reasoning (CBR)
- both in science and in industrial applications. It starts with a short introduction
to the essential ideas and concepts CBR is built upon... / diagnosis configuration planning and design. In the last part we br configuration tasks and end with planning and design. . Some
Using Context to Scale the On-line Evolution of Animat-"Minds" - Birk, Paul (1999)(Correct)
Evolutionary Computation techniques are popular and promising approaches to
an autonomous construction of animate-"minds" as controllers and world-models for
animal-like robots. But in a life-long lea... / have dominated this field. But planning capabilities and thus br be used for a crude form of planning. A pointer in the graph the
Data-Driven Theory Refinement Using KBDistAl - Yang, Parekh, Honavar, Dobbs (1999)(Correct)
Knowledge based artificial neural networks offer an attractive
approach to extending or modifying incomplete knowledge bases or
domain theories through a process of data-driven theory refinement. ... / Allstate Research Planning Ctr Middlefield Rd Menlo br time constructive neural network learning algorithm. The initial domain
MINERVA: A Second-Generation Museum Tour-Guide Robot - Thrun, Bennewitz, Burgard, Cremers.. (1999)(Correct)
This paper describes an interactive tour-guide robot, which
was successfully exhibited in a Smithsonian museum. During
its two weeks of operation, the robot interacted with
more than 50,000 people, tr... / collision avoidance path planning and global mission planning. br path planning and global mission planning. The interaction modules
Achieving Coordination through Combining Joint Planning and Joint.. - Weiss (1999)(Correct)
There are two major approaches to activity coordination in multiagent systems.
First, by endowing the agents with the capability to jointly plan, that is, to jointly
generate hypothetical activity ... / through Combining Joint Planning and Joint Learning Gerhard Wei br new algorithm called JPJL Joint Planning and Joint Learning that
Self-Adapting Genetic Algorithms with an Application to Project.. - Sönke Hartmann (1999)(Correct)
This paper introduces a new general framework for genetic algorithms to solve a
broad range of optimization problems. When designing a genetic algorithm, there may
be several alternatives for a compon... / leitstand systems for production planning. Applying the self-adapting br That is the genetic algorithm learns which of the alternative
How Can Psychology Help Artificial Intelligence - Val (1999)(Correct)
This paper discusses the relationship between Artificial Intelligence
(AI) and Psychology. As an AI practicioner, I'll let psychologists evaluate
the impact of AI, or more generally computational mode... / them to correct errors even planning for the possibility of error to br most research in automated planning until not long ago would proceed
Notes on methods based on maximum-likelihood estimation for learning.. - Ortiz, Kaelbling (1999)(Correct)
In these notes, we present and review di erent methods based on maximum-likelihood
estimation for learning the parameters of the mixture-of-Gaussians model. We describe
a method based on the likelihoo... / Fellowship and by DARPA Rome Labs Planning Initiative grant br in part by DARPA Rome Labs Planning Initiative grant
Hierarchical Optimization of Policy-Coupled Semi-Markov Decision.. - Gang Wang, Sridhar Mahadevan (1999)(Correct)
One general strategy for approximately
solving large Markov decision processes is
"divide-and-conquer": the original problem
is decomposed into sub-problems which interact
with each other, but yet can... / agents including sensing planning learning and acting are being br set such as in the air campaign planning problem and the composite
Synthetic News Radio: Content Filtering and Delivery for Broadcast.. - Emnett (1999)(Correct)
Synthetic News Radio uses automatic speech recognition and clustered text news stories to automatically
find story boundaries in an audio news broadcast, and it creates semantic representations that c... / School of Architecture and Planning in partial fulfillment of the br School of Architecture and Planning on May in partial
Experiments with an EEG-based computer interface - Penny, Roberts (1999)(Correct)
We report on experiments with an EEG-based computer interface
developed at Imperial College. The experiments are inspired by a programme
of research in Albany by Wolpaw et al. We first briefly review
... / reduce in power during movement planning imagination or execution. br to be correlated with movement planning and imagery. Pfurtscheller et
Accelerating EM: An Empirical Study - Luis Ortiz (1999)(Correct)
Many applications require that we learn the parameters
of a model from data. EM (ExpectationMaximization)
is a method for learning the parameters
of probabilistic models with missing or
hidden data. T... / Fellowship and by DARPA Rome Labs Planning Initiative grant br in part by DARPA Rome Labs Planning Initiative grant
Plan Mining by Divide-and-Conquer - Jiawei Han (1999)(Correct)
Plans or sequences of actions are an important form of data. With the proliferation of database technology,
plan databases (or planbases) are increasingly common. Efficient discovery of important patt... / methods in hierarchical planning. We illustrate our approach using br our approach using a travel planning database. Introduction In
Sequential Optimality and Coordination in Multiagent Systems - Boutilier (1999)(Correct)
Coordination of agent activities is a key problem in multiagent systems. Set in a larger decision theoretic context, the existence of coordination problems leads to difficulty in evaluating the utilit... / activities ranging from logistics planning to robotic soccer. An obvious br and S. Hanks. Decision theoretic planning Structural assumptionsand
Learned rewrite rules versus learned search control rules to improve.. - Upal, Elio (1999)(Correct)
Domain independent planners can produce better-quality plans through the use of domain-dependent knowledge,
typically encoded as search control rules. The planning-by-rewriting approach has been propo... / Abstract Domain independent planners can produce better-quality plans br as search control rules. The planning-by-rewriting approach has been
Model based Bayesian Exploration - Dearden, Friedman, Andre (1999)(Correct)
Reinforcement learning systems are often concerned
with balancing exploration of untested actions against
exploitation of actions that are known to be good. The
benefit of exploration can be estimated... / in learning is balancing between planning i.e.choosing a policy and br architectures for learning planning and reacting based on
An Architecture For Distributed Cooperative-Planning In A.. - Jung, Zelinsky (1999)(Correct)
The Architecture for Behaviour-Based Agents
(ABBA) is an architecture designed to illustrate
that situated agents can exhibit sophisticated
planning while retaining reactivity, without
resorting to h... / For Distributed Cooperative-Planning In A Behaviour-Based br agents can exhibit sophisticated planning while retaining reactivity
Rapid Concurrent Software Engineering in Competitive Situations - Hannebauer, Wendler.. (1999)(Correct)
This article is an experience report on the evolutionary
development process of AT Humboldt, a multi
agent system which has become World Champion 1997
and Vice World Champion 1998 of RoboCup simulator... / This ruled out classical planning approaches which took to much br attainability predicate a layered planner and a continuation enforcement
Learning User Evaluation Functions for Adaptive Scheduling Assistance - Gervasio, Iba, Langley (1999)(Correct)
Inca is an adaptive, interactive assistant for crisis response. In this
paper, we present Inca's advisable interaction framework, wherein
users can guide the search toward particular solutions by prov... / library to seed the interactive planning and scheduling phases of crisis br response. The primary purpose of planning is to choose a set of actions or
Maintenance scheduling problems as benchmarks for constraint.. - Frost, Dechter (1999)(Correct)
The paper focuses on evaluating constraint satisfaction search algorithms on application
based random problem instances. The application we use is a well-studied
problem in the electric power industry... / required to meet throughout the planning period are known in advance. The br and maintenance costs over the planning period subject to various
Value-Update Rules for Real-Time Search - Sven Koenig (1999)(Correct)
Real-time search methods have successfully been used to
solve a large variety of search problems but their properties
are largely unknown. In this paper, we study how existing
real-time search methods... / on the other hand interleave planning and plan execution and allow br control over how much planning to perform between plan
Real-time Collision Detection for Virtual Surgery - Lombardo, Cani, Neyret (1999)(Correct)
We present a simple method for performing real-time
collision detection in a virtual surgery environment. The
method relies on the graphics hardware for testing the interpenetration
between a virtual ... / are often required in motion planning application. In our background br the operation onto a screen. Learning to coordinate the motion of the
The Dynamics of Intelligence: Constraint-Satisfying Hybrid Systems.. - Mackworth (1999)(Correct)
Methods for designing and building perceptual agents
should be clean, powerful and practical. But no
methodology satisfies all three criteria, yet. Our
methodologies are evolving dialectically. The sy... / perception reasoning and planning with online models of low-level br bootstrapping or by itself learning A robot is typically a
A Multi-Agent Architecture for Cooperative Software Engineering - Wang, Conradi, Liu (1999)(Correct)
This paper looks at how Cooperative Software Engineering (CSE) can be supported. We first investigate
the process aspects by presenting a traditional process architecture supporting CSE. Then we propo... / work together in an organised and planned way partly pre-planned For br and planned way partly pre-planned For high-level processes it is
A Connectionist Approach... - Goller (1999)(Correct)
The central problem in automated deduction
is the explosive growth of search spaces when
proof length increases. In this paper, a connectionist
approach for learning search-control
heuristics for auto... / knowledge-based systems planning deductive data bases and the br A Connectionist Approach for Learning Search-Control Heuristics for
Evolutionary Group Robots for Collective World Modeling - Jiming Liu, Jianbing Wu (1999)(Correct)
This paper is concerned with collective problem-solving with a
group of autonomous agents. The major challenges addressed are
(1) how to enable the distributed agents to dynamically acquire
their goal... / and or real-time reactive motion planning Also unlike the br potential field approach to path planning. IEEE Transactions on Robotics
Text Classification by Bootstrapping with Keywords, EM and Shrinkage - McCallum, Nigam (1999)(Correct)
When applying text classification to complex
tasks, it is tedious and expensive
to hand-label the large amounts of training
data necessary for good performance.
This paper presents an alternative appr... / Interface Design design Planning knowledge representation br code language natural planning documents Computer Science
Learning Discrete Bayesian Models for Autonomous Agent Navigation - Nikovski (1999)(Correct)
Partially observable Markov decision processes (POMDPs) are a convenient representation for reasoning and planning in mobile robot applications. We investigate two algorithms for learning POMDPs from ... / representation for reasoning and planning in mobile robot applications. We br worlds in conjunction with four planning algorithms. Experimental results
Developing a Knowledge Management Technology - An Encompassing View.. - Abecker, Bernardi, Sintek (1999)(Correct)
In this short position paper, we sketch three ongoing projects
(KnowMore, ENRICH, and Know-Net) currently running
in the Knowledge Management Group of DFKI investigating
requirements and approaches to... / tasks like design or strategic planning collaboration of several br intertwined teaching and use of planning methodologies such as Total
Exploring Unknown Environments with Real-Time Search or Reinforcement .. - Koenig (1999)(Correct)
Learning Real-Time A* (LRTA*) is a popular control method that interleaves planning
and plan execution and has been shown to solve search problems in known
environments efficiently. In this paper, we ... / control method that interleaves planning and plan execution and has been br dynamic programming interleave planning and plan execution and exhibit
Approximate Planning in Large POMDPs via Reusable Trajectories - Kearns, Mansour, Ng (1999)(Correct)
We consider the problem of reliably choosing a near-best strategy from a restricted class of strategies \Pi in a partially observable Markov decision process (POMDP). In particular, we are interested ... / Approximate Planning in Large POMDPs via Reusable br discuss a number of practical planning algorithms for POMDPs that arise
A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov .. - Kearns, Mansour, Ng (1999)(Correct)
An issue that is critical for the application of
Markov decision processes (MDPs) to realistic
problems is how the complexity of planning
scales with the size of the MDP. In stochastic
environments wi... / Algorithm for Near-Optimal Planning in Large Markov Decision br problems is how the complexity of planning scales with the size of the MDP.
Mining GPS Data to Augment Road Models - Rogers, Langley, Wilson (1999)(Correct)
Many advanced safety and navigation applications in vehicles require accurate, detailed
digital maps, but manual lane measurements are expensive and time-consuming, making automated
techniques desirab... / in continuous domains. Some planning-based systems that interact with br to achieve a goal expected from planning they attempt to correct their
Initial Experiments in Stochastic Satisfiability - Littman (1999)(Correct)
Both satisfiability problems and probabilistic models
are popular in artificial intelligence and computer
science. This paper looks at the rich intersection
between these two topics, opening the
door ... / of these ideas viewing planning under uncertainty as br special cases of P-Sat and planning and reasoning under uncertainty.
A Proof Presentation Suitable for Teaching Proofs - Melis, Leron (1999)(Correct)
The paper addresses comprehensible proof presentation for
teaching and learning that can be provided by an automated proof planner
that is a component of the proof development
environment\Omega
meg... / be provided by an automated proof planner that is a component of the proof br their capabilities its proof planner should produce a output
The CMUnited-98 Champion Simulator Team - Stone, Veloso, Riley (1999)(Correct)
The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66--0. CMUnited-98 builds upon the successful CMUni... / by the DARPA RL Knowledge Based Planning and Scheduling Initiative under br players. However for strategic planning it is very useful to have a
On Texts, Cases, and Concepts - Lenz, Glintschert (1999)(Correct)
The management of textual information is getting more and
more attention within the case-based reasoning community. In this paper,
we will address the question of how a case base can be obtained fro... / Document Finder machine learning techniques for automatically
Multi-Value-Functions: Efficient Automatic Action Hierarchies for.. - Andrew Moore (1999)(Correct)
Actions come from?", and whether it is necessary to have some high-level
prior understanding of the class of tasks at hand in order to decide which abstractions are beneficial. We
hope that this may b... / memory by performing most of the planning at a high level between br is very small. Figure Planning the next action from the
Empirical Evidence for Derivational Analogy - Schmid, Carbonell (1999)(Correct)
Analogical problem solving is mostly described as transfer of a
source solution to a target problem based on the structural correspondences
(mapping) between source and target. Derivational
analogy (C... / Susan and Joshua Epstein are planning a trip to five tropical islands br in old castles. One summer they planned a holiday trip to Germany where
Learning Policies for Attentional Control - Goncalves, Giraldi, Oliveira, Grupen (1999)(Correct)
In this work we propose two behavioraly active policies for attentional control. These policies must
act based on a multi-modal sensory feedback. Two approaches are used to derive the policies: the ... / and eventually navigation or path-planning. We adopt an active behavioral br Learning Policies for Attentional Control
A New Method to Index and Query Sets - Hoffmann, Koehler (1999)(Correct)
Let us consider the following problem:
Given a (probably huge) set of sets S and
a query set q, is there some set s 2 S such
that s ` q? This problem occurs in at
least four application areas: the mat... / during artificial intelligence planning and the detection of potential br in the IPP system and enabled this planner to win the ADL track of the
Ontology-based Process Support - Schnurr, Staab, Studer (1999)(Correct)
This paper describes a principled approach towards creating
an IT-support environment for knowledge workers. Starting
in the analysis phase our approach paves the way for putting
an intelligent assist... / following we first draft a project planning scenario that will then serve as br methodological approach. Project Planning Scenario Let us here consider
Analytical and Experimental Results on Multiagent Cooperative.. - Jiming Liu, Jianbing Wu, Xun Lai (1999)(Correct)
This paper addresses the problem of automatically programming cooperative behaviors in a group of autonomous robots. The
specific task that we consider here is for a group of distributed autonomous ro... / modeling limitations as well as planning costs as in many real-life br each robot a sophisticated motion planner that will take into consideration
Transversal Graphs For Partially Ordered Sets: Sequencing, Merging.. - Middendorf, Timkovsky (1999)(Correct)
This paper introduces an approach to solving combinatorial optimization problems
on partially ordered sets by the reduction to searching source-sink paths in the related
transversal graphs. Di ere... / applications in molecular biology learning theory data compression br and M. Li On the complexity of learning strings and sequences Theoret.
Learned Models for Continuous Planning - Matthew Schmill (1999)(Correct)
We are interested in the nature of activity --
structured behavior of nontrivial duration --
in intelligent agents. We believe that the development
of activity is a continual process
in which simpler ... / Learned Models for Continuous Planning Matthew D. Schmill Tim Oates br activities are composed via planning to form more sophisticated ones
Memory for Goals: An Architectural Perspective - Altmann, Trafton (1999)(Correct)
The notion that memory for goals is organized as a stack
persists as a central feature of cognitive theory, in that
stacks are primitive mechanisms in leading cognitive architectures.
However, the sta... / Thus the order in which steps are planned conference then airplane is br are pushed in the order they are planned and popped in the order they are
Case-Based Problem Solving for Knowledge Management Systems - Becerra-Fernandez, Aha (1999)(Correct)
Case Based Reasoning (CBR) is an intelligent systems
methodology that enables information managers to increase
efficiency and reduce cost by substantially automating processes
(i.e., diagnosis, schedu... / distributed crisis response planning tasks Aha et al. b CCBR br the organization into a learning organization that continues to
The AAAI-99 KM/CBR Workshop: Summary of Contributions - Aha (1999)(Correct)
The contributions at the AAAI-99 Workshop on Exploring Synergies of Knowledge
Management and Case-Based Reasoning (www.aic.nrl.navy.mil/~aha/aaai99-kmcbrw)
were varied; it was the first AAAI workshop ... / on enterprise resource planning O'Leary using ontologies br Schnurr et al. project planning Mauer Holz
Towards Intelligent Virtual Environment for Training Medical Doctors.. - Alo, Aló, Kreinovich (1999)(Correct)
Chronic pain is a serious health problem affecting
millions of people worldwide. Spinal cord stimulation
is one of the most effective methods of easing the
chronic pain. For most patients, a careful s... / all of them. . What we are planning to do In this paper we br simulator to help the doctors learn this technique. ffl Second
Design by Autonomous Learning: Modeling Environment for Design of.. - Prabhakar, Smith (1999)(Correct)
this paper, we consider the environments that are closed, accessible and deterministic. We
first present the overall architecture of the IMPEDe methodology. Then present a control
strategy for interac... / Integrated Modeling Planning and Execution for Design br also has a set of methods for planning modeling and learning the
A Hierarchical Self-Organizing Map Model In Short-Term Load.. - Carpinteiro, Silva (1999)(Correct)
This paper proposes a novel neural model to the problem of short-term load forecasting. The
neural model is made up of two self-organizing map nets --- one on top of the other. It has
been successfull... / power system problems such as planning control analysis protection br recovered. A strategy must be planned to avoid this situation. V
The Use of Fuzzy Measures in Pain Relief Control - Vladik Kreinovich (1999)(Correct)
this paper, we show that a further progress can be
obtained if we use the idea of a fuzzy measure.
6 What is a Fuzzy Measure and Why This
Notion May Be Useful in Pain Relief
6.1 Traditional Mathemat... / all of them. What We Are Planning to Do In our previous papers br simulator to help the doctors learn this technique. ffl Second the
What Should the Tutor Do When the Student Cannot Answer a Question? - Yujian Zhou (1999)(Correct)
In this paper we describe how to simulate the behavior of a
human tutor when the student cannot answer a question in a
dialogue-based tutoring system. This paper describes an
implementation of our ana... / implemented them in the current planning framework. This paper shows that br this section we will describe the planner in CST v. then discuss how we
A controlled experiment on the effects of PSP training: Detailed.. - Prechelt, Unger (1999)(Correct)
The Personal Software Process (PSP) is a methodology for systematic and continuous improvement
of an individual software engineer's software production capabilities. The proponents of the
PSP claim th... / several goals ffl Reliable planning capability i.e.the ability to br domain because otherwise the PSP planning may break down and the results
Predicting the Speed of Beer Fermentation in Laboratory and.. - Rousu, Elomaa, Aarts (1999)(Correct)
Characteristic of the beer production process is the uncertainty
caused by the complex biological raw materials and the yeast, a
living organism. This uncertainty is exempliøed by the fact that pred... / variations can be diminished by re-planning the mashing recipes The br slightly. A fermentation recipe planner such as the Sophist system
Design of a Genetic-Fuzzy System for Planning Crab Gaits of a.. - Pratihar, Deb, Ghosh (1999)(Correct)
This paper describes a genetic-fuzzy system in which a genetic algorithm (GA) is used to improve
the performance of a fuzzy logic controller (FLC). The proposed algorithm is tested on a number of
gait... / of a Genetic-Fuzzy System for Planning Crab Gaits of a Six-legged Robot br frame and body frame GA based learning Knowledge Base Fuzzy System
Towards a Vision System for Supervising Assembly Processes - Bauckhage, Fritsch, Kummert, Sagerer (1999)(Correct)
Supervising robotic assembly of multi-functional objects by means of a computer vision system requires
components to identify assembly operations and to recognize feasible assemblies of single objec... / Assembly Inferred Reactive Planning disappeared Assemblies new and br is similar to the notation for planning operators. To infer for example
A Practical One-Semester "VLSI Design" Course for Computer Science.. - Walker (1999)(Correct)
This paper describes the development and content of a
"VLSI Design" course. We had two main goals for the
course: to develop a one-semester course for computer
science (and other) majors, and to give ... / logic design or IC operation. The planning stage for the course was fairly br key insight that arose during this planning was that there was no way we
Adapting to User Preferences in Crisis Response - Wayne Iba (1999)(Correct)
The domain of crisis planning and scheduling taxes human
response managers due to high levels of urgency and uncertainty.
Such applications require assistant technologies
(in contrast to automation te... / ABSTRACT The domain of crisis planning and scheduling taxes human br should relieve the user of planning and scheduling details but also
Toward Opening Book Learning - Michael Buro (1999)(Correct)
In this article an opening book framework for
game--playing programs is presented. Motivated
by basic requirements for successfully
playing a sequence of games --- such as avoiding
losing games twice ... / stemming from a lack of strategic planning. In order to circumvent this br Toward Opening Book Learning Michael Buro NEC Research
Artificial Life, Adaptive Behavior, Agents Application Oriented.. - Tony White (1999)(Correct)
The statistical properties associated with applications
using the resources of a network have natural synergies
when considering measured quality of service. However,
it is difficult to know in advanc... / are possible. An offline or planning solution is possible. In this br routing fault location and planning. . The Model The model for
Accelerating Learning from Experience: Avoiding Defects Faster - Lutz Prechelt (1999)(Correct)
Over time, any programmer will learn from repeated mistakes. Can we speed up this learning
and save many unnecessary repetitions of similar errors? This article presents a technique
called "defect log... / effort estimation and time planning techniques and a complete br research results Accelerating Learning from Experience Avoiding
Practical Architectures for Survivable Systems and Networks.. - Neumann (1999)(Correct)
This report summarizes the analysis of survivability-related requirements
and their interdependence. It also identifies inadequacies in existing commercial
systems and the absence of components that... / as early as for Fall of and planning to integrate some of this br toleration of compromises must be planned in system design for cases in
Efficient Mining of Statistical Dependencies - Oates, Cohen, Durfee (1999)(Correct)
this
paper, we describe three methods for reducing the size of the search space that msdd considers and
empirically evaluate their utility. The remainder of this section discusses the core msdd algori... / b learning probabilistic planning operators Oates Cohen a br and Cohen P. R. a. Learning planning operators with conditional and
Fast Synthetic Vision, Memory, and Learning Models for Virtual Humans - Kuffner, Jr., Latombe (1999)(Correct)
This paper presents a simple and efficient method of
modeling synthetic vision, memory, and learning for autonomous
animated characters in real-time virtual environments.
The model is efficient in ter... / is inspired by research in motion planning control and sensing for br We combine a low-level path planner a pathfollowing controller and
Robots in the Classroom - Tools for Accessible Education - Martyn Cooper (1999)(Correct)
In this paper we describe some of the current and envisaged uses of this broad collection of
technologies referred to as robots, within education. This is firstly from the general
perspective but then... / mechanics measurement task planning programming mathematical br generally in key elements of the learning process. Robots are a great aid
An Indexed Bibliography of Genetic Algorithms - Papers of 1996 (in.. - Jarmo T. Alander (1999)(Correct)
s: Jan. 1995 -- Sep. 1998
ffl ACM: ACM Guide to Computing Literature: 1979 -- 1993/4
ffl BA: Biological Abstracts: July 1996 - Aug. 1998
ffl CA: Computer Abstracts: Jan. 1993 -- Feb. 1995
ffl CCA:... / Evolving Shape Robot Planning power Analysis br help to those who are working or planning to work in this rapidly growing
Learning Maps for Indoor Mobile Robot Navigation - Thrun (1998)(Correct)
Autonomous robots must be able to learn and maintain models of their environments.
Research on mobile robot navigation has produced two major paradigms for mapping indoor
environments: grid-based and ... / often prohibits efficient planning and problem solving in br approaches a they permit fast planning b they facilitate interfacing
Optimization and global minimization methods suitable for neural.. - Duch, Korczak (1998)(Correct)
Neural networks are usually trained using local, gradient-based procedures. Such methods frequently
find suboptimal solutions being trapped in local minima. Optimization of neural structures and globa... / using typical gradient-based learning techniques starting from a large br neural networks are able to learn many non-trivial problems since
Scalable and Adaptive Goal Recognition - Lesh (1998)(Correct)
Scalable and Adaptive Goal Recognition
by Neal Lesh
Chairperson of Supervisory Committee: Professor Oren Etzioni
Department of Computer Science
and Engineering
Goal recognition is the task of inferri... / on work in machine learning and planning for scaling up goal recognition br Bibliography Appendix A Planning definitions Appendix B Data
The Omnipresence of Case-Based Reasoning in Science and Application - Aha (1998)(Correct)
A surprisingly large number of research disciplines have contributed towards the
development of knowledge on lazy problem solving, which is characterized by its storage
of ground cases and its demand ... / cognitive psychology process planning statistics have also br Software reuse Process Planning Variant process planning .
Learning Models for Robot Navigation - Shatkay (1998)(Correct)
Hidden Markov models (hmms) and partially observable Markov decision processes (pomdps)
provide a useful tool for modeling dynamical systems. They are particularly useful for representing
environments... / typical for robot navigation and planning. The work presented here br sound method for localization and planning SK NPB CKK Most other
Adaptive Behavior in Autonomous Agents - Ziemke (1998)(Correct)
This paper gives an overview of the bottom-up approach to artificial intelligence
(AI), commonly referred to as behavior-oriented AI. The behavior-oriented approach,
with its focus on the interaction ... / cognitive capacities such as planning problem solving or game br into a central world model. A planner based on this internal
Learning to Take Actions - Khardon (1998)(Correct)
We formalize a model for supervised learning of action strategies in dynamic stochastic
domains and show that PAC-learning results on Occam algorithms hold in this model
as well. We then identify a cl... / to what is done in the study of planning Allen Hendler Tate br action strategies in small planning domains that have been studied
Using Multi-Strategy Learning to Improve Planning Efficiency and.. - Estlin (1998)(Correct)
viii
Chapter 1 Introduction 1
1.1 Acquiring Planning Control Knowledge . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Scope: A Control Knowledge Acquisition System . . . . . . . . . . . . . ... / Learning to Improve Planning Efficiency and Quality Tara br Learning to Improve Planning Efficiency and Quality by
Methodological Issues for Designing Multi-Agent Systems with Machine.. - Drogoul, Zucker (1998)(Correct)
This paper deals with one of the probably most challenging and, in our
opinion, little addressed question that can be found in Distributed Artificial
Intelligence today, that of the methodological des... / natural language processing to planning or problem solving. The br agent will consist in selecting planning those actions that lead to an
Learning Control of Complex Skills - Crawford (1998)(Correct)
Learning Control of Complex Skills
by
Lara Sidonie Crawford
Doctor of Philosophy in
Biophysics
University of California at Berkeley
Professor S. Shankar Sastry, Chair
This dissertation presents a hi... / problem for standard control and planning algorithms conservation of br Another possibility is that planning is done in terms of force and
Scalable Services For Video-On-Demand - Chan, Tobagi (1998)(Correct)
Video-on-demand (VOD) refers to video services in which users can request any video
program from a server at any time. VOD has important applications in entertainment, education,
information, and adve... / schemes and addressed the channel planning and profit issues in such a br we use simulation. Bandwidth planning As an example we consider T
Combining Artificial Intelligence and Databases for Data Integration - Levy (1998)(Correct)
Data integration is a problem at the intersection of the fields of Artificial Intelligence and
Database Systems. The goal of a data integration system is to provide a uniform interface to a
multitude ... / extracting data from sources and planning techniques for query br and of techniques for interleaving planning and execution for the purpose of
Map Learning and High-Speed Navigation in RHINO - Thrun, Bücken, Burgard, Fox.. (1998)(Correct)
This chapter surveys basic methods for learning maps and high speed autonomous navigation for indoor
mobile robots. The methods have been developed in our lab over the past few years, and most of them... / constructed that facilitate fast planning. . Localization. Localization br Approaches to global path planning exploration and reactive
Affordances for acting in direct manipulation interfaces - Amant (1998)(Correct)
This article describes the theory, shows how existing interface mechanisms
fit into its conceptual framework, identifies novel interface affordances suggested by the framework, and outlines procedures... / used in artificial intelligence planning systems. This article describes br inevitably involves search. Planning is a kind of search appropriate
Individual Learning of Coordination Knowledge - Sen, Sekaran (1998)(Correct)
Social agents, both human and computational, inhabiting a world containing
multiple active agents, need to coordinate their activities. This is
because agents share resources, and without proper coord... / like knowledge representation planning learning non-monotonic br Simon ffl multi-agent planning Durfee and Lesser
The Role of Assumptions in Knowledge Engineering - Fensel, Benjamins (1998)(Correct)
Problem-solving methods are means to describe the inference process
of knowledge-based systems. During the last years, a number of these problemsolving
methods have been identified that can be reuse... / by Benjamins and for planning by Barros et al. br solving Fensel et al. planning Barros et al. and develop
A Computational Approach for Argumentative Discourse in Multi-Agent.. - Karacapilidis (1998)(Correct)
This paper describes a Group Decision Support System for cooperative or non-cooperative argumentative discourses. The system provides agents means of expressing and weighing their individual arguments... / related regional and federal Planning Departments environmental br refers to e.g. cooperative planning iii basicElements
An Architecture for Cooperation among Autonomous Agents - Jung (1998)(Correct)
This thesis develops the Architecture for Behaviour Based Agents (ABBA) -- an architecture
suitable for supporting the distributed planning of cooperative behaviour in multi-robot
systems. ABBA was us... / for supporting the distributed planning of cooperative behaviour in br spatial and topological path planning using a homogeneous action
Generalization - Wah (1998)(Correct)
In this paper, we define the generalization problem, summarize various approaches in
generalization, identify the credit assignment problem, and present the problem and some
solutions in measuring gen... / space and involves experiment planning instance selection and result br Space Rule Space Experiment Planning Instance Selection Result
Alternative Essences of Intelligence - Brooks, (Ferrell), Irie, Kemp.. (1998)(Correct)
We present a novel methodology for building humanlike
artificially intelligent systems. We take as a model
the only existing systems which are universally accepted
as intelligent: humans. We emphasize... / one sees a continuing interest in planning Littman Hauskrecht br jug does not need to be explicitly planned or controlled since it is the
Probabilistic Reasoning As Information Compression By Multiple.. - Wolff (1998)(Correct)
This report introduces the idea that probabilistic reasoning (PrbRs) may be understood as
information compression by multiple alignment, unification and search (ICMAUS). In this
context, multiple alig... / language processing planning and problem solving not yet br .Appendix A reviews some of the planned future developments in this
Module-Based Reinforcement Learning: Experiments with a Real Robot - Kalmár, al. (1998)(Correct)
The behavior of reinforcement learning (RL) algorithms is best understood in completely observable, discrete-time controlled Markov chains with finite state and action spaces. In contrast, robot-lea... / Simon and Korf a in planning domains. The attractive property br Korf In the framework of planning with MDPs the plan acceleration
An Interpretation of the "Self " From the Dynamical Systems.. - Tani (1998)(Correct)
This study attempts to describe the notion of the "self" using dynamical systems
language based on the results of our robot learning experiments. A neural network
model consisting of multiple modules ... / such as recognition learning or planning it has not made a great br as abstraction representation or planning. Instead the focus was on the
Modelling Users, Intentions, and Structure in Spoken Dialog - Ludwig, Görz, Niemann (1998)(Correct)
We outline how utterances in dialogs can be interpreted using a partial first order logic.
We exploit the capability of this logic to talk about the truth status of formulae to define a
notion of cohe... / be taken into account by studying planning of utterances. Discourse br planning of utterances. Discourse planning is discussed extensively e.g. by
User Models, Dialog Structure, and Intentions in Spoken Dialog - Ludwig, Görz, Niemann (1998)(Correct)
this paper
In this paper we present empirical evidence that in spoken dialogs all approaches
outlined in the last section are important for a general model of
dialog and robust dialog managers. We arg... / relevant discourse plans. In these planning approaches one reasons from a br can transfer attitudes and reflect planning steps of dialog participants
BISMARC: A Biologically Inspired System for Map-based Autonomous.. - Huntsberger, Rose (1998)(Correct)
As the complexity of the missions to planetary surfaces increases, so too does the
need for autonomous rover systems. This need is complicated by the power, mass
and computer storage restrictions on s... / of the brain is activated for path planning but not for landmark br the Earth. Such a mission is being planned by NASA in with the Sample
State-Based SHOSLIF for Indoor Visual Navigation - Chen, Weng (1998)(Correct)
In this paper, we investigate vision-based navigation using the Self-organizing Hierarchical
Optimal Subspace Learning and Inference Framework (SHOSLIF) that incorporates states and a
visual attention... / for high-level semantically based planning. These above systems predefine br Hierarchical Optimal Subspace Learning and Inference Framework SHOSLIF
Learning Hierarchical Behaviors - Andre (1998)(Correct)
In the last few years, many researchers have begun to study how to introduce hierarchy
into reinforcement learning methods. Generally, this work has pushed the envelope in one of
several important d... / similarity between deterministic planning domains and reinforcement br perform value propagation steps planning during learning. These
Reinforcement Learning for Autonomous Three-Dimensional Object.. - Paletta, Prantl, Pinz (1998)(Correct)
An active observer with the task to identify a three-dimensional object is involved in a search for discriminative
viewpoints. This paper defines the recognition process as a sequential decision pro... / loop the agent learns a sensor planning strategy by reinforcing behavior br a reliable decision. E.g.a view planning system provides choices among a
Class-Based Control Schemes for Parameterized Project Scheduling.. - Schirmer, Riesenberg (1998)(Correct)
Most scheduling problems are notoriously intractable, so the majority of algorithms for
them are heuristic in nature. Priority rule-based methods still constitute the most important class of
these... / by considering the periods of the planning horizon in chronological order. br critical-path method Resources planning and scheduling in Industrial
Bayesian Models for Keyhole Plan Recognition in an Adventure Game - Albrecht, Zukerman, Nicholson (1998)(Correct)
We present an approach to keyhole plan recognition which uses a dynamic belief (Bayesian)
network to represent features of the domain that are needed to identify users' plans and goals. The
applicat... / acquisition of information about planning in an effort to overcome this br generated the mental state and planning process of the agent and the
Multilevel Simulation and Numerical Optimization of Complex.. - Schwabacher, Gelsey (1998)(Correct)
Multilevel representations have been studied
extensively by artificial intelligence researchers.
We present a general method that
utilizes the multilevel paradigm to attack the
problem of performing m... / Multilevel techniques for planning and theorem proving go back as br Sacerdoti E. D. Planning in a Hierarchy of Abstraction
Constructive Theory Refinement in Knowledge Based Neural Networks - Parekh, Honavar (1998)(Correct)
Knowledge based artificial neural networks offer
an approach for connectionist theory refinement. We
present an algorithm for refining and extending the domain
theory incorporated in a knowledge based... / with the Allstate Research and Planning Center in Menlo Park br using constructive neural network learning algorithms. The initial domain
On Natural Life's Tricks to Survive and Evolve - Schwefel, Kursawe (1998)(Correct)
Which are the fundamental principles of life? This is the main question to be addressed if one tries to create artificial life on computers. Though it has been answered only partially, evolutionary al... / hard design management and planning as well as control problems. br optimum seeking without individual learning. Keywords-evolutionary
Ecological Robotics: A Schema-theoretic Approach - Arkin (1998)(Correct)
Schema
Language (ASL)
MissionLab (Mlab)
Perceptual-Motor
Weitzenfeld
Arkin Cervantes
Predictions
Results
Common Language
Simulations Robot Experiments Biological Data
Neural Simulation
Language (NSL... / to motivational factors and learning processes. The animal's response br ffl Time-varying Dynamics learning processes require at least the
Heuristic Algorithms for Solving the Resource-Constrained Project.. - Kolisch, Hartmann (1998)(Correct)
Introduction
The resource constrained project scheduling problem (RCPSP) can be given as follows. A single
project consists of a set J = f0; 1; : : : ; n; n+1g of activities which have to be processe... / by Pritsker et al. The planning horizon is divided in T br Activity networks Project planning and control by network models.
In-Context Information Management through Adaptive Collaboration of.. - Sycara (1998)(Correct)
Although the number and availability of electronic information sources are increasing,
current information technology requires manual manipulation and userspecification
of all details. Once accessed, ... / fulfill the delegated goals. The planning takes place in an open br is an integral part of the planning process. Thus the context of
Forming Independent Components via Temporal Locking of Reconstruction .. - Lörincz (1998)(Correct)
The assumption is made that the formulation of relations as independent components (IC) is a main feature of computations accomplished by the brain. Further, it is assumed that memory traces made of n... / problems such as path planning tasks Hwang YK and Ahuja N br and Ahuja N Gross motion planning -a survey. ACM Computing
Hierarchical Reinforcement Learning with the MAXQ Value Function.. - Dietterich (1998)(Correct)
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ
decomposition of the value function. The MAXQ decomposition has both a procedural semantics---
as a subrouti... / much recent work on probabilistic planning and learning. Formally a br discounted case. In probabilistic planning it is assumed that the agent
Adaptive Parallel Iterative Deepening Search - Cook, al. (1998)(Correct)
Many of the artificial intelligence techniques developed to date rely on heuristic search
through large spaces. Unfortunately, the size of these spaces and the corresponding computational
effort reduc... / artificial search spaces and planning problems indicate that Eureka br Rao and robot arm path planning Challou Gini Kumar
High-Level Planning and Control with Incomplete Information Using.. - Geffner, Bonet (1998)(Correct)
We develop an approach to planning with incomplete
information that is based on three elements:
1. a high-level language for describing the effects of
actions on both the world and the agent's beliefs... / High-Level Planning and Control with Incomplete br We develop an approach to planning with incomplete information that
Using Explicit Requirements and Metrics for Interface Agent User.. - Brown, Jr. (1998)(Correct)
The complexity of current computer systems and software
warrants research into methods to decrease the cognitive
load on users. Determining how to get the right information
into the right form with th... / class stereotypes a causal planning model represented as a Bayesian br reasoning and machine learning. The strength of HCI research in
Grounding Symbols through Sensorimotor Integration - MacDorman (1998)(Correct)
and inferential coherence. They lack these
aspects because their underlying methods have been
unable to deal e ectively with constituent structure,
though more elaborate implementations should overc... / symbolic modeling reasoning and planning e.g.Nilsson Rodney br without thinking about them. . Planned implementation of ro We now
Utility Theory-Based User Models for Intelligent Interface Agents - Brown, Santos, Jr., Banks (1998)(Correct)
An underlying problem of current interface agent research is
the failure to adequately address effective and efficient knowledge representations
and associated methodologies suitable for modeling th... / many times users do not follow pre-planned goals. They perform actions that br Jameson describes how a causal planning model can be used to construct
Rational Error Correction - Tinsley (1998)(Correct)
Under general conditions, linear decision rules of agents with rational expectations are
equivalent to restricted error corrections. However, empirical rejections of rational expectation
restriction... / one a lead system for the forward planning required by polynomial frictions br discount factor over the infinite planning horizon. To complete the
Goal-Directed Navigation for Animated Characters Using Real-Time Path .. - Kuffner, Jr. (1998)(Correct)
This paper presents a new technique for computing collisionfree
navigation motions from task-level commands for animated human
characters in interactive virtual environments. The algorithm implement... / Characters Using Real-Time Path Planning and Control James J. Kuffner br cards to perform fast D motion planning. Given a D geometric
Building Knowledge Bases with situations to help the cooperative.. - Poittevin (1998)(Correct)
This paper describes REVINOS, an incremental modeling and cooperative revision tool
for Knowledge Bases (KB) expressed with situation nodules. Situation nodules are simple and
understandable objects... / no memory and are incapable of planning. What they do is reacting to br are made automatically by machine learning techniques. . Introduction
A Next Generation Information Gathering Agent - Lesser, Horling, Klassner, Raja.. (1998)(Correct)
The World Wide Web has become an invaluable information resource but the explosion of information available via the web has made web search a time consuming and complex process. Index-based search eng... / Agents Information Systems Planning Scheduling Text Processing. br technologies namely scheduling planning text processing information
Experimental Evaluation of State-of-the-Art Heuristics for the.. - Hartmann, Kolisch (1998)(Correct)
This paper is a follow--
up study which provides an in--depth investigation of the performance of recent RCPSP heuristics.
We give a detailed performance of the heuristics and provide explanations for... / are fixed and incapable of learning from previously evaluated br have the inherent property of learning i.e.self-adaptation.
On the relations between Intelligent Backtracking and Failure-driven.. - Kambhampati (1998)(Correct)
The ideas of intelligent backtracking (IB) and explanation-based learning (EBL) have developed independently in the constraint satisfaction, planning, machine learning and problem solving communities.... / Relations between IB EBL in Planning and CSP On the relations br In Constraint Satisfaction And Planning Asu Cse Tr - Subbarao
Synthesizing Customized Planners from Specifications - Biplav Srivastava (1998)(Correct)
Existing plan synthesis approaches in artificial intelligence fall into two categories --
domain independent and domain dependent. The domain independent approaches are applicable
across a variety of ... / Synthesizing Customized Planners from Specifications Biplav br synthesize domain independent planners given the knowledge about the
Learning Situation-Dependent Costs: Improving Planning from.. - Haigh, Veloso (1998)(Correct)
Real world robot tasks are so complex that it is hard to
hand-tune all of the domain knowledge, especially to model
the dynamics of the environment. Several research efforts
focus on applying machine ... / Costs Improving Planning from Probabilistic Robot br learning techniques for robot planning. The goal is to use real robotic
Active Markov Localization for Mobile Robots - Fox, Burgard, Thrun (1998)(Correct)
Localization is the problem of determining the position of a mobile robot from sensor data. Most existing
localization approaches are passive, i.e., they do not exploit the opportunity to control the ... / with robot control e.g.the planning community assumes that the br In our implementation a global planning module uses dynamic programming
Cortical dynamics and biomechanics - Bailly (1998)(Correct)
Movement generation is the complex result of the interaction between viscoelastic properties of muscle, inertial properties
of the musculo-skeletal system and spatial trajectory planning. The Equilibr... / system and spatial trajectory planning. The Equilibrium Hypothesis EP br a priori the problem of trajectory planning and on-line control of speech
Planning Tutorial Text in a System for Teaching English as a Second.. - Michaud, McCoy (1998)(Correct)
In this paper we discuss an envisioned text planner for
a computer-assisted instruction tool for deaf learners
of English. We describe the problem of deaf literacy
and overview our system, designed to... / Planning Tutorial Text in a System for br paper we discuss an envisioned text planner for a computer-assisted
Learning sorting and decision trees with POMDPs - Bonet, Geffner (1998)(Correct)
pomdps are general models of sequential decisions
in which both actions and observations
can be probabilistic. Many problems of
interest, including extracting decision trees
from data, can be formulat... / such as robot navigation and planning are beginning to be formulated br such as robot navigation and planning are beginning to be formulated
Flexible and Scalable Query Planning in Distributed and Heterogeneous .. - Ambite, Knoblock (1998)(Correct)
We present the application of the Planning by Rewriting
(PbR) framework to query planning in distributed
and heterogeneous environments. PbR is a new
paradigm for efficient high-quality planning that ... / Flexible and Scalable Query Planning in Distributed and Heterogeneous br We present the application of the Planning by Rewriting PbR framework to
The Interactive Museum Tour-Guide Robot - Burgard, Cremers, Fox, Hähnel.. (1998)(Correct)
This paper describes the software architecture of an autonomous
tour-guide/tutor robot. This robot was recently
deployed in the "Deutsches Museum Bonn," were it guided
hundreds of visitors through the... / mapping localization path planning mission planning and user br path planning mission planning and user interface control. The
acQuire-macros: An Algorithm for Automatically Learning Macro-actions - McGovern (1998)(Correct)
ion and Hierarchy in Reinforcement Learning 1
acQuire-macros: An Algorithm for Automatically Learning
Macro-actions
Amy McGovern
amy@cs.umass.edu
Computer Science Department
University of Massachus... / new methods for learning and planning with such actions e.g. br Decomposition techniques for planning in stochastic domains. Technical
Modelling Motivational Behaviour In Intelligent Agents In Virtual.. - Burt (1998)(Correct)
The MAS group at the DFKI is developing architectures
for animated agents in virtual worlds.
Within the tradition of AI there are many techniques
that can be used to model the cognitive abilities
of s... / of symbolic processing such as planning or learning inherited from br capability of the agent. A local-planning layer that can generate
The Learning Curves Underlying Convergence - Gaines (1998)(Correct)
The convergence of telecommunications and computing technologies and services into a new
medium offering integrated services through digital networks was predicted in the 1970s and is
beginning to hav... / off when too little is known for planned progress is that of the inventor br research development and product planning targeted on that impact but
Macro-Actions in Reinforcement Learning: An Empirical Analysis - McGovern, Sutton (1998)(Correct)
Several researchers have proposed reinforcement learning methods that obtain advantages
in learning by using temporally extended actions, or macro-actions, but none
has carefully analyzed what these a... / new methods for learning and planning with such actions. In this br the walker to skip thinking or planning at the level of muscle movements
Heading in the Right Direction - Shatkay, Kaelbling (1998)(Correct)
Stochastic topological models, and hidden
Markov models in particular, are a useful tool
for robotic navigation and planning. In previous
work we have shown how weak odometric
data can be used to impr... / tool for robotic navigation and planning. In previous work we have shown br typical for robot navigation and planning Previous work on
Theoretical Results on Reinforcement Learning with Temporally.. - Precup, Sutton, Singh (1998)(Correct)
Behaviors
Doina Precup
1
, Richard S. Sutton
1
, and Satinder Singh
2
1
Department of Computer Science
University of Massachusetts
Amherst, MA 01003-4610
http://www.cs.umass.edu/f~dprecupj~richg... / present new theoretical results on planning within the framework of br making system that involves planning and prediction. In temporally
Genetic Programming and Deductive-Inductive Learning: a.. - Aler, Borrajo, Isasi (1998)(Correct)
Genetic Programming (GP) is a machine
learning technique that was not conceived
to use domain knowledge for generating new
candidate solutions. It has been shown that
GP can benefit from domain knowle... / rules for problem solving in planning. Results show that both methods br approaches use domain independent planners for generating plans Blum and
An RBF Network Alternative for a Hybrid Architecture - Peterson, Sun (1998)(Correct)
Although our previous model CLARION has
shown some measure of success in reactive sequential decision
making tasks by utilizing a hybrid architecture which
uses both procedural and declarative learnin... / and thus integrating reaction planning learning and decision-making. br based on reinforcement learning planning and teaching. Machine Learning
Learning Optimal Dialogue Strategies: A Case Study of a Spoken.. - Walker, Fromer, Narayanan (1998)(Correct)
This paper describes a novel method by which a dialogue
agent can learn to choose an optimal dialogue
strategy. While it is widely agreed that dialogue
strategies should be formulated in terms of comm... / Meeting.Decision theoretic planning can be applied to the problem of br . M.T. Maybury. . Planning multi-media explanations using
Team-Partitioned, Opaque-Transition Reinforcement Learning - Stone, Veloso (1998)(Correct)
In this paper, we present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement
learning (TPOT-RL). TPOT-RL introduces the concept of using action-dependent fe... / by the DARPA RL Knowledge Based Planning and Scheduling Initiative under br Opaque-Transition Reinforcement Learning Peter Stone and Manuela Veloso
Learning Situation-Dependent Rules: Improving Planning from Robot.. - Haigh, Veloso (1998)(Correct)
Real world robot tasks are so complex that it is hard
to hand-tune all of the domain knowledge, especially
to model the dynamics of the environment. In this paper
we present techniques for learning fr... / Rules Improving Planning from Robot Execution Karen br robot execution to improve planning and execution performance. We
Remembering to Add: Competence-preserving Case-Addition Policies for.. - Zhu, Yang (1998)(Correct)
Case-base maintenance is gaining increasing
recognition in research and the practical applications
of case-based reasoning (CBR). This
intense interest is highlighted by Smyth and
Keane's research on ... / an experiment in case-based planning. Introduction Case-base br we demonstrate through case-based planning how to construct high-quality
Techniques and Knowledge used for Adaptation during Case-Based.. - Wilke, Bergmann (1998)(Correct)
This paper presents an overview of different adaptation methods which are common in today's
systems. We introduce first the process model of CBR and the used knowledge according to the
different knowl... / including prediction diagnosis planning process and quality control br like configuration design or planning the vast space of possible
Programmable Pattern Generators - Schaal, Sternad (1998)(Correct)
This paper explores the idea to create complex
human-like arm movements from movement primitives
based on nonlinear attractor dynamics. Each degree-offreedom
of an arm is assumed to have two indepen... / potential field approaches for planning e.g.Koditschek and br in one framework task specific planning that can exploit both intrinsic
Pattern separation via ellipsoids and conic programming - Glineur (1998)(Correct)
this document.
The first chapter is about mathematical programming. We will start by describing how
and why researchers were led to study special types of mathematical programs, namely convex
programs... / numerical parameters to tune planning etc.in order to find the best br linear programs e.g. production planning transportation scheduling etc.
Dynamic Hypertext Catalogues: Helping Users to Help Themselves - Milosavljevic, Oberlander (1998)(Correct)
Electronic hypertext catalogues provide an important channel
for information provision. However, static hypertext documents
cannot be dynamically adapted to help the user find
what he/she is looking f... / It can be viewed as a goal-driven planning process involving the br are borrowed from conventional planning techniques developed within
A Language for Reconfigurable Robot Control - Nabbe (1998)(Correct)
When robots are to be deployed in urban environments, these robots need to be able to cope with all kinds of terrain. Includes curbs, steps and even stairs. A reconfigurable robot is best used in thes... / software and the high level planning software. The Con guration br tuples for all possible goals. The planner stacks its desired goals on the
Learning from Ambiguity - Maron (1998)(Correct)
There are many learning problems for which the examples given by the teacher are
ambiguously labeled. In this thesis, we will examine one framework of learning from
ambiguous examples known as Multipl... / it on the MUSK dataset. I had been planning to do that eventually but it br Learning from Ambiguity by Oded
Multiple Adaptive Agents for Tactical Driving - Sukthankar, Baluja, Hancock (1998)(Correct)
Recent research in automated highway systems has ranged from low-level vision-based controllers
to high-level route-guidance software. However, there is currently no system for tactical-level
reason... / to this intermediate-level planning is a system which consists of a br strategic level a route is planned and goals are determined at the
Learning Weakly Acyclic Horn Programs - Reddy, Tadepalli (1998)(Correct)
We consider a general class of "weakly acyclic Horn programs" where the literals
implied by the examples and the target clauses form an acyclic dependency graph. A
Horn clause is transparent if all th... / as above in the blocks world planning can be learned by our program. br control knowledge to make planning efficient. One kind of control
Programming by Analogy: Retrieval, Mapping, Adaptation and.. - Schmid, Mercy, Wysotzki (1998)(Correct)
We present an approach to program reuse by analogical transfer based upon the notion of recursive program
schemes (RPSs). RPSs are representations which capture the structure of a program and are ex... / are generated by backward planning with production rules br representing constants. We are planning to modify our system accordingly
ANCORS: Adaptable Network COntrol and Reporting System - Livio Ricciulli (1998)(Correct)
We propose to merge network management, active networking, and distributed
simulation in a unified paradigm to assist in the assessment, control, and design of
computer networks. We explore some of th... / paradigm will extend to planning performance and stability br are needed to test efficacy of planned security measures and ascertain