Contribution to the study and the design of reinforcement functions
The underlying concept in Reinforcement Learning is as simple as it is attractive: to learn by trial and error from the interaction with the environment. This approach allows us to deal with problems where a learning technique searches to improve the performance of the agent (the learner) over time....
Guardado en:
Autor principal: | |
---|---|
Formato: | Articulo |
Lenguaje: | Español |
Publicado: |
2000
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/135464 https://publicaciones.sadio.org.ar/index.php/EJS/article/view/127 |
Aporte de: |
id |
I19-R120-10915-135464 |
---|---|
record_format |
dspace |
institution |
Universidad Nacional de La Plata |
institution_str |
I-19 |
repository_str |
R-120 |
collection |
SEDICI (UNLP) |
language |
Español |
topic |
Ciencias Informáticas Reinforcement Learning Artificial Neural Networks |
spellingShingle |
Ciencias Informáticas Reinforcement Learning Artificial Neural Networks Santos, Juan Miguel Contribution to the study and the design of reinforcement functions |
topic_facet |
Ciencias Informáticas Reinforcement Learning Artificial Neural Networks |
description |
The underlying concept in Reinforcement Learning is as simple as it is attractive: to learn by trial and error from the interaction with the environment. This approach allows us to deal with problems where a learning technique searches to improve the performance of the agent (the learner) over time. Reinforcement Learning groups a set of such techniques, and it uses a performance measure based on two types of signals given by a Critic or Reinforcement Function: penalty and reward. |
format |
Articulo Articulo |
author |
Santos, Juan Miguel |
author_facet |
Santos, Juan Miguel |
author_sort |
Santos, Juan Miguel |
title |
Contribution to the study and the design of reinforcement functions |
title_short |
Contribution to the study and the design of reinforcement functions |
title_full |
Contribution to the study and the design of reinforcement functions |
title_fullStr |
Contribution to the study and the design of reinforcement functions |
title_full_unstemmed |
Contribution to the study and the design of reinforcement functions |
title_sort |
contribution to the study and the design of reinforcement functions |
publishDate |
2000 |
url |
http://sedici.unlp.edu.ar/handle/10915/135464 https://publicaciones.sadio.org.ar/index.php/EJS/article/view/127 |
work_keys_str_mv |
AT santosjuanmiguel contributiontothestudyandthedesignofreinforcementfunctions |
bdutipo_str |
Repositorios |
_version_ |
1764820455392280577 |