Sciweavers

JAIR
2000
131views more  JAIR 2000»
13 years 11 months ago
An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email
This paper describes a novel method by which a spoken dialogue system can learn to choose an optimal dialogue strategy from its experience interacting with human users. The method...
Marilyn A. Walker
JAIR
2000
123views more  JAIR 2000»
13 years 11 months ago
Backbone Fragility and the Local Search Cost Peak
The local search algorithm WSat is one of the most successful algorithms for solving the satisfiability (SAT) problem. It is notably effective at solving hard Random 3-SAT instanc...
Josh Singer, Ian P. Gent, Alan Smaill
JAIR
2000
100views more  JAIR 2000»
13 years 11 months ago
On the Compilability and Expressive Power of Propositional Planning Formalisms
The recent approaches of extending the GRAPHPLAN algorithm to handle more expressive planning formalisms raise the question of what the formal meaning of "expressive power&qu...
Bernhard Nebel
JAIR
2000
94views more  JAIR 2000»
13 years 11 months ago
Planning Graph as a (Dynamic) CSP: Exploiting EBL, DDB and other CSP Search Techniques in Graphplan
This paper reviews the connections between Graphplan's planning-graph and the dynamic constraint satisfaction problem and motivates the need for adapting CSP search technique...
Subbarao Kambhampati
JAIR
2000
96views more  JAIR 2000»
13 years 11 months ago
OBDD-based Universal Planning for Synchronized Agents in Non-Deterministic Domains
Recently model checking representation and search techniques were shown to be efciently applicable to planning, in particular to non-deterministic planning. Such planning approach...
Rune M. Jensen, Manuela M. Veloso
JAIR
2000
152views more  JAIR 2000»
13 years 11 months ago
Value-Function Approximations for Partially Observable Markov Decision Processes
Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in whic...
Milos Hauskrecht
JAIR
2000
66views more  JAIR 2000»
13 years 11 months ago
Space Efficiency of Propositional Knowledge Representation Formalisms
Marco Cadoli, Francesco M. Donini, Paolo Liberator...
JAIR
2000
102views more  JAIR 2000»
13 years 11 months ago
A Model of Inductive Bias Learning
A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem bein...
Jonathan Baxter
JAIR
2000
105views more  JAIR 2000»
13 years 11 months ago
Reasoning on Interval and Point-based Disjunctive Metric Constraints in Temporal Contexts
We introduce a temporal model for reasoning on disjunctive metric constraints on intervals and time points in temporal contexts. This temporal model is composed of a labeled tempo...
Federico Barber