A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning

Mostrar todas las versiones(2)

Optimization of hyper-parameters in real-world applications of reinforcement learning (RL) is a key issue, because their settings determine how fast the agent will learn its policy by interacting with its environment due to the information content of data gathered. In this work, an approach that use...

Descripción completa

Detalles Bibliográficos
Autores principales:	Barsce, Juan Cruz, Palombarini, Jorge, Martínez, Ernesto
Formato:	Articulo
Lenguaje:	Inglés
Publicado:	2020
Materias:	Ciencias Informáticas Reinforcement learning hyper-parameter optimization Bayesian optimization Bayesian optimization of combinatorial structures (BOCS)
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/135049 https://publicaciones.sadio.org.ar/index.php/EJS/article/view/165
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-135049
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 Reinforcement learning hyper-parameter optimization Bayesian optimization Bayesian optimization of combinatorial structures (BOCS)
spellingShingle	Ciencias Informáticas Reinforcement learning hyper-parameter optimization Bayesian optimization Bayesian optimization of combinatorial structures (BOCS) Barsce, Juan Cruz Palombarini, Jorge Martínez, Ernesto A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning
topic_facet	Ciencias Informáticas Reinforcement learning hyper-parameter optimization Bayesian optimization Bayesian optimization of combinatorial structures (BOCS)
description	Optimization of hyper-parameters in real-world applications of reinforcement learning (RL) is a key issue, because their settings determine how fast the agent will learn its policy by interacting with its environment due to the information content of data gathered. In this work, an approach that uses Bayesian optimization to perform an autonomous two-tier optimization of both representation decisions and algorithm hyper-parameters is proposed: first, categorical / structural RL hyper-parameters are taken as binary variables and optimized with an acquisition function tailored for such type of variables. Then, at a lower level of abstraction, solution-level hyper-parameters are optimized by resorting to the expected improvement acquisition function, whereas the categorical hyper-parameters found in the optimization at the upper level of abstraction are fixed. This two-tier approach is validated with a tabular and neural network setting of the value function, in a classic simulated control task. Results obtained are promising and open the way for more user-independent applications of reinforcement learning.
format	Articulo Articulo
author	Barsce, Juan Cruz Palombarini, Jorge Martínez, Ernesto
author_facet	Barsce, Juan Cruz Palombarini, Jorge Martínez, Ernesto
author_sort	Barsce, Juan Cruz
title	A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning
title_short	A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning
title_full	A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning
title_fullStr	A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning
title_full_unstemmed	A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning
title_sort	hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
publishDate	2020
url	http://sedici.unlp.edu.ar/handle/10915/135049 https://publicaciones.sadio.org.ar/index.php/EJS/article/view/165
work_keys_str_mv	AT barscejuancruz ahierarchicaltwotierapproachtohyperparameteroptimizationinreinforcementlearning AT palombarinijorge ahierarchicaltwotierapproachtohyperparameteroptimizationinreinforcementlearning AT martinezernesto ahierarchicaltwotierapproachtohyperparameteroptimizationinreinforcementlearning AT barscejuancruz hierarchicaltwotierapproachtohyperparameteroptimizationinreinforcementlearning AT palombarinijorge hierarchicaltwotierapproachtohyperparameteroptimizationinreinforcementlearning AT martinezernesto hierarchicaltwotierapproachtohyperparameteroptimizationinreinforcementlearning
bdutipo_str	Repositorios
_version_	1764820456035057666

A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning

Ejemplares similares