Using combination of actions in reinforcement learning

Software agents are programs that can observe their environment and act in an attempt to reach their design goals. In most cases the selection of particular agent architecture determines the behaviour in response to the different problem states However, there are some problem domains in which it is...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Karanik, Marcelo J., Gramajo, Sergio D.
Formato: Articulo
Lenguaje:Inglés
Publicado: 2010
Materias:
Ciencias Informáticas
Learning
SARSA
optimal policy
action combination
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/9663
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr10-4.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-9663
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
Learning
SARSA
optimal policy
action combination
spellingShingle Ciencias Informáticas
Learning
SARSA
optimal policy
action combination
Karanik, Marcelo J.
Gramajo, Sergio D.
Using combination of actions in reinforcement learning
topic_facet Ciencias Informáticas
Learning
SARSA
optimal policy
action combination
description Software agents are programs that can observe their environment and act in an attempt to reach their design goals. In most cases the selection of particular agent architecture determines the behaviour in response to the different problem states However, there are some problem domains in which it is desirable that the agent learns a good action execution policy by interacting with its environment. This kind of learning is called Reinforcement Learning and it is useful in the process control area. Given a problem state, the agent selects the adequate action to do and receives an immediate reward, then estimations about every action are updated and, after a certain period of time, the agent learns which the best action to be executed is. Most reinforcement learning algorithms perform simple actions while two or more are capable of being used. This work involves the use of RL algorithms to find an optimal policy in a gridworld problem and proposes a mechanism to combine actions of different types.
format Articulo
Articulo
author Karanik, Marcelo J.
Gramajo, Sergio D.
author_facet Karanik, Marcelo J.
Gramajo, Sergio D.
author_sort Karanik, Marcelo J.
title Using combination of actions in reinforcement learning
title_short Using combination of actions in reinforcement learning
title_full Using combination of actions in reinforcement learning
title_fullStr Using combination of actions in reinforcement learning
title_full_unstemmed Using combination of actions in reinforcement learning
title_sort using combination of actions in reinforcement learning
publishDate 2010
url http://sedici.unlp.edu.ar/handle/10915/9663
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr10-4.pdf
work_keys_str_mv AT karanikmarceloj usingcombinationofactionsinreinforcementlearning
AT gramajosergiod usingcombinationofactionsinreinforcementlearning
bdutipo_str Repositorios
_version_ 1764820492309495814

Ejemplares similares