Contribution to the study and the design of reinforcement functions

Mostrar todas las versiones(5)

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....

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Santos, Juan Miguel
Formato: Articulo
Lenguaje:Español
Publicado: 2000
Materias:
Ciencias Informáticas
Reinforcement Learning
Artificial Neural Networks
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/135464
https://publicaciones.sadio.org.ar/index.php/EJS/article/view/127
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
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

Ejemplares similares