Título: A study in using temporal abstraction and function approximation in reinforcement learning /
Autores: Mouadeb, Mark.
Fecha: 2006
Publicador: McGill University - MCGILL
Fuente:
Tipo: Electronic Thesis or Dissertation
Tema: Computer Science.
Descripción: The incorporation of temporally extended actions, or options , into the reinforcement learning framework has proven to be useful in planning and knowledge representation. Options provide a form of temporal abstraction, as they represent courses of action of variable duration. At the same time, agents operating in large domains often require the use of function approximation in order to generalize their experience over many states. Previous research has demonstrated the theoretical properties and usefulness of options in small domains where function approximation is not necessary. However, the theoretical and empirical properties of options with function approximation are still not well understood. In this thesis, we investigate the performance of options with the CMAC function approximator on an implementation of the game Asteroids (Atari, 1979). Our results demonstrate that options can be integrated successfully with function approximation. If good options are available, they can facilitate faster learning.
Idioma: en