Título
Automatic discovery of concepts for unknown environments
Autor
ANA CECILIA TENORIO GONZALEZ
Colaborador
EDUARDO FRANCISCO MORALES MANZANARES (Asesor de tesis)
Nivel de Acceso
Acceso Abierto
Materias
Concept learning - (CONCEPTO DE APRENDIZAJE) Reinforcement learning - (APRENDIZAJE REFORZADO) Predicate invention - (PREDICE LA INVENCIÓN) Inductive logic programming - (PROGRAMACIÓN LÓGICA INDUCTIVA) CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA - (CTI) MATEMÁTICAS - (CTI) CIENCIA DE LOS ORDENADORES - (CTI)
Resumen o descripción
This thesis explores how an agent can autonomously learn about its environment
just by interacting with it. This is not an easy task, since traditional
machine learning algorithms strongly depend on the user's intervention to define
the data to use and the experimental conditions under which the learning
process takes place. Designing an agent that autonomously drives its own
learning process poses several interesting challenges. How to explore the environment,
how to gather and represent the information obtained from the
environment (what to learn, when to learn, and how to organize the new
knowledge) and how to evaluate the knowledge acquired. In this thesis, an
algorithm called ADC which combines different machine learning techniques
in novel ways, is proposed to answer these questions. In particular, a novel
exploration strategy is proposed based on an asymmetric Wundt's curve and
biased actions to guide an agent through the environment and the learning
process. ADC incrementally builds, during exploration, a graph-based
representation of the environment using some initial background knowledge.
Frequent sub-graphs are automatically identified as instances of potentially
useful concepts from which relational concepts are induced. These concepts
are organized in a lattice and incorporated into its background knowledge
so that they can be used for learning new concepts. ADC also learns how
to perform new tasks by reinforcement learning with intrinsic motivation,
relational concepts are used to define states where actions are learned. The
learned behavior policies are stored for solving future tasks. ADC was tested
on simulated environments (floors, polygons, furniture, mobility and stability
of objects) and the concepts learned by the system were validated by
independent users (different to the author of this thesis) with encouraging
results. Among the learned concepts are basic structures (e.g., room), polygons
(e.g., pentagon, triangle), furniture (e.g., table, chair), movable objects,
and examples of simple stable structures.
Editor
Instituto, Nacional de Astrofísica, Óptica y Electrónica
Fecha de publicación
junio de 2016
Tipo de publicación
Tesis de doctorado
Recurso de información
Formato
application/pdf
Idioma
Inglés
Audiencia
Público en general
Sugerencia de citación
Tenorio-Gonzalez A.C.
Repositorio Orígen
Repositorio Institucional del INAOE
Descargas
507