A parallel implementation of Q-learning based on communication with cache
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...
| Autores principales: | , , |
|---|---|
| Formato: | Articulo |
| Lenguaje: | Inglés |
| Publicado: |
2002
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/9432 http://journal.info.unlp.edu.ar/wp-content/uploads/p41.pdf |
| Aporte de: |
| id |
I19-R120-10915-9432 |
|---|---|
| record_format |
dspace |
| institution |
Universidad Nacional de La Plata |
| institution_str |
I-19 |
| repository_str |
R-120 |
| collection |
SEDICI (UNLP) |
| language |
Inglés |
| topic |
Ciencias Informáticas Parallel programming Redes de Comunicación de Computadores Informática Aprendizaje communication based on cache reinforcement learning asynchronous dynamic programming |
| spellingShingle |
Ciencias Informáticas Parallel programming Redes de Comunicación de Computadores Informática Aprendizaje communication based on cache reinforcement learning asynchronous dynamic programming Printista, Alicia Marcela Errecalde, Marcelo Luis Montoya, Cecilia Inés A parallel implementation of Q-learning based on communication with cache |
| topic_facet |
Ciencias Informáticas Parallel programming Redes de Comunicación de Computadores Informática Aprendizaje communication based on cache reinforcement learning asynchronous dynamic programming |
| description |
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. |
| format |
Articulo Articulo |
| author |
Printista, Alicia Marcela Errecalde, Marcelo Luis Montoya, Cecilia Inés |
| author_facet |
Printista, Alicia Marcela Errecalde, Marcelo Luis Montoya, Cecilia Inés |
| author_sort |
Printista, Alicia Marcela |
| title |
A parallel implementation of Q-learning based on communication with cache |
| title_short |
A parallel implementation of Q-learning based on communication with cache |
| title_full |
A parallel implementation of Q-learning based on communication with cache |
| title_fullStr |
A parallel implementation of Q-learning based on communication with cache |
| title_full_unstemmed |
A parallel implementation of Q-learning based on communication with cache |
| title_sort |
parallel implementation of q-learning based on communication with cache |
| publishDate |
2002 |
| url |
http://sedici.unlp.edu.ar/handle/10915/9432 http://journal.info.unlp.edu.ar/wp-content/uploads/p41.pdf |
| work_keys_str_mv |
AT printistaaliciamarcela aparallelimplementationofqlearningbasedoncommunicationwithcache AT errecaldemarceloluis aparallelimplementationofqlearningbasedoncommunicationwithcache AT montoyaceciliaines aparallelimplementationofqlearningbasedoncommunicationwithcache AT printistaaliciamarcela parallelimplementationofqlearningbasedoncommunicationwithcache AT errecaldemarceloluis parallelimplementationofqlearningbasedoncommunicationwithcache AT montoyaceciliaines parallelimplementationofqlearningbasedoncommunicationwithcache |
| bdutipo_str |
Repositorios |
| _version_ |
1764820491166547969 |