- Inicio
- Atrás
|
Título: |
A parallel implementation of Q-learning based on communication with cache |
Autores: |
Printista, Alicia Marcela Errecalde, Marcelo Luis Montoya, Cecilia Inés |
Fecha: |
2004-02-09 2002 |
Publicador: |
Unversidad Nacional de La Plata |
Fuente: |
|
Tipo: |
Articulo Articulo |
Tema: |
parallel programming; communication based on cache; reinforcement learning; asynchronous dynamic programming Ciencias Informáticas Reinforcement Learning Memorias Cache Redes de Comunicación de Computadores Informática Aprendizaje |
Descripción: |
Q-Learning is a Reinforcement Learning method for solving sequential decision problems, where the utility of actions depends on a sequence of decisions and there exists uncertainty about the dynamics of the environment the agent is situated on. This general framework has allowed that Q-Learning and other Reinforcement Learning methods to be applied to a broad spectrum of complex real world problems such as robotics, industrial manufacturing, games and others. Despite its interesting properties, Q-learning is a very slow method that requires a long period of training for learning an acceptable policy. In order to solve or at least reduce this problem, we propose a parallel implementation model of Q-learning using a tabular representation and via a communication scheme based on cache. This model is applied to a particular problem and the results obtained with different processor configurations are reported. A brief discussion about the properties and current limitations of our approach is finally presented. |
Idioma: |
Inglés |