Year: 2003
Type: dissertation
Abstract: Being able to represent and reason about the world as though it were composed of "objects" seems like a useful abstraction.The typical approach to representing a world composed of objects is to use a relational representation; however, other representations, such as deictic representations, have also been studied.I am interested not only in an agent that is able to represent objects, but in one that is also able to act in order to achieve some task.This requires the ability to learn a plan of action.While value-based approaches to learning plans have been studied in the past, both with relational and deictic representations, I believe the shortcomings uncovered by those studies can be overcome by the use of a world model.Knowledge about how the world works has the advantage of being re-usable across specific tasks.In general, however, it is difficult to obtain a completely specified model about the world.This work attempts to characterize an approach to planning in a relational domain when the world model is represented as a potentially incomplete and/or redundant set of uncertain rules.
Authors: Hernandez Gardiol, Natália Natália
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2254376175