Abstraction in Reinforcement Learning: Using Option Discovery and State Similarity - Tapa blanda

Girgin, Sertan

 
9783639136524: Abstraction in Reinforcement Learning: Using Option Discovery and State Similarity
Tapa blanda
ISBN 10: 3639136527 ISBN 13: 9783639136524
Editorial: VDM Verlag, 2009

Sinopsis

Reinforcement learning is the problem faced by an agent that must learn behavior through trial-and-error interactions with a dynamic environment. Usually, the problem to be solved contains subtasks that repeat at different regions of the state space. Without any guidance an agent has to learn the solutions of all subtask instances independently, which in turn degrades the performance of the learning process. In this work, we propose two novel approaches for building the connections between different regions of the search space. The first approach efficiently discovers abstractions in the form of conditionally terminating sequences and represents these abstractions compactly as a single tree structure; this structure is then used to determine the actions to be executed by the agent. In the second approach, a similarity function between states is defined based on the number of common action sequences; by using this similarity function, updates on the action-value function of a state are re?ected to all similar states that allows experience acquired during learning be applied to a broader context. The effectiveness of both approaches is demonstrated empirically over various domains.

"Sinopsis" puede pertenecer a otra edición de este libro.

Reseña del editor

Reinforcement learning is the problem faced by an agent that must learn behavior through trial-and-error interactions with a dynamic environment. Usually, the problem to be solved contains subtasks that repeat at different regions of the state space. Without any guidance an agent has to learn the solutions of all subtask instances independently, which in turn degrades the performance of the learning process. In this work, we propose two novel approaches for building the connections between different regions of the search space. The first approach efficiently discovers abstractions in the form of conditionally terminating sequences and represents these abstractions compactly as a single tree structure; this structure is then used to determine the actions to be executed by the agent. In the second approach, a similarity function between states is defined based on the number of common action sequences; by using this similarity function, updates on the action-value function of a state are reflected to all similar states that allows experience acquired during learning be applied to a broader context. The effectiveness of both approaches is demonstrated empirically over various domains.

Biografía del autor

Sertan Girgin received his Ph.D. degree in Computer Engineering from Middle East Technical University, Turkey in 2007 and holds a double major in Mathematics. His research interests include Reinforcement Learning, Distributed AI and Multi Agent Systems, Biologically Inspired Robotics and Evolutionary Algorithms.

"Sobre este título" puede pertenecer a otra edición de este libro.

Editorial
VDM Verlag
Año de publicación
2009
Idioma
Inglés
ISBN 10 
3639136527
ISBN 13 
9783639136524
Encuadernación
Tapa blanda
Número de páginas
104
Contacto del fabricante
no disponible
Persona responsable
no disponible