Sciweavers

ICAI
2004
13 years 10 months ago
Transient Region Coverage in the Propulsion IVHM Technology Experiment
Edward Balaban, William A. Maul, Adam Sweet, Chris...
ICAI
2004
13 years 10 months ago
Plan Understanding: Inferring Implicit Dependencies from Explicit Elements in Multi-Agent Plan Representations
Current planning systems often fail to represent the reasons why certain planning decisions are made. Explicit representation of this Plan Rationale is crucial for automated plan m...
James P. Allen, Phil DiBona
ICAI
2004
13 years 10 months ago
Action Inhibition
An explicit exploration strategy is necessary in reinforcement learning (RL) to balance the need to reduce the uncertainty associated with the expected outcome of an action and the...
Myriam Abramson
ICAI
2004
13 years 10 months ago
Mixed-Initiative Ontology Learning
This paper presents a mixed-initiative assistant that supports a subject matter expert to extend the ontology of a learning agent, in order to express the subtle distinctions he ma...
Cristina Boicu, Gheorghe Tecuci
ICAI
2004
13 years 10 months ago
Task Oriented Machine-Learning and Review
We propose an optimization algorithm to execute a previously unlearned task-oriented command in an intelligent machine. We show that a well-defined, physically bounded, task-orien...
Pierre Abdelmalek, Howard E. Michel
ICAI
2004
13 years 10 months ago
Genetic Programming Reconsidered
Even though the Genetic Programming (GP) mechanism is capable of evolving any computable function, the means through which it does so is inherently flawed: the user must provide th...
Russ Abbott, Behzad Parviz, Chengyu Sun
ICAI
2004
13 years 10 months ago
Towards Developing Behavior Based Control Architectures for Mobile Robots Using Simulated Behaviors
This paper proposes the Simulated Behaviors Approach for using simulation to investigate the structure and function of control architectures for behavior based mobile robots. The ...
J. N. Bishop, Walter D. Potter
ICAI
2004
13 years 10 months ago
Potential-Based Processing for Action-Game Experimentation
Abstract-- We define a framework for what we call potentialbased computing and show how it may be applied to actionmotion applications in general and dynamic games in particular. W...
Russ Abbott, Valentino Crespi