Mostrando 8 resultados de: 8
Filtros aplicados
Publisher
2017 21st International Conference on System Theory, Control and Computing, ICSTCC 2017(1)
2018 7th International Conference on Systems and Control, ICSC 2018(1)
IEEE Transactions on Artificial Intelligence(1)
IEEE Transactions on Control Systems Technology(1)
IFAC-PapersOnLine(1)
Área temáticas
Ciencias de la computación(4)
Métodos informáticos especiales(2)
Programación informática, programas, datos, seguridad(2)
Ciencias sociales(1)
Funcionamiento de bibliotecas y archivos(1)
A linear programming methodology for approximate dynamic programming
ArticleAbstract: The linear programming (LP) approach to solve the Bellman equation in dynamic programming is a well-Palabras claves:approximate dynamic programming, Control Applications, linear programming, Neural networksAutores:Armesto L., Henry Díaz, Sala A.Fuentes:scopusApproximate dynamic programming methodology for data-based optimal controllers
ArticleAbstract: In this article, we present a methodology for learning data-based approximately optimal controllers,Palabras claves:approximate dynamic programming, Intelligent Control, Neural Learning, Optimal ControlAutores:Armesto L., Henry Díaz, Sala A.Fuentes:scopusFitted Q-Function Control Methodology Based on Takagi-Sugeno Systems
ArticleAbstract: This paper presents a combined identification/Q-function fitting methodology that involves identificPalabras claves:Adaptive dynamic programing (DP), fitted Q-function, Linear Matrix Inequality (LMI), reinforcement learning (RL), Takagi-Sugeno (TS)Autores:Armesto L., Henry Díaz, Sala A.Fuentes:scopusHierarchical Reinforcement Learning for Air Combat At DARPA's AlphaDogfight Trials
ArticleAbstract: Autonomous control in high-dimensional, continuous state spaces is a persistent and important challePalabras claves:Air combat, Artificial Intelligence, Atmospheric modeling, Autonomy, Deep reinforcement learning, entropy, hierarchical reinforcement learning, reinforcement learning, Task analysis, TRAINING, WeaponsAutores:Alcedo K., Henry Díaz, Ide J.S., Javorsek D., Micovic D., Pope A.P., Ritholtz L., Rosenbluth D., Twedt J.C., Walker T.T.Fuentes:scopusImprovement of LMI controllers of Takagi-Sugeno models via Q-learning
Conference ObjectAbstract: This paper presents a preliminary attempt to bridge the conservative (shape-independent) results froPalabras claves:adaptive dynamic programming, LMI, Q-Learning, reinforcement learning, Takagi-SugenoAutores:Armesto L., Henry Díaz, Sala A.Fuentes:scopusImproving LMI controllers for discrete nonlinear systems using policy iteration
Conference ObjectAbstract: This paper presents a method to improve the conservative (shape-independent) controllers from guaranPalabras claves:LMI, policy iteration (pI), Q-Learning, reinforcement learning, Takagi-SugenoAutores:Armesto L., Henry Díaz, Sala A.Fuentes:scopusLearning Upper-Level Policy using Importance Sampling-based Policy Search Method
Conference ObjectAbstract: Policy search methods are a successful approach to reinforcement learning. These allow to learn uppePalabras claves:Autores:Armesto L., Esparza A., Henry Díaz, Pastor J., Sala A.Fuentes:scopusLearning an Improved LMI Controller Based on Takagi-Sugeno Models via Value Iteration
Conference ObjectAbstract: This article proposes an alternative for formulating the method to improve the conservative controllPalabras claves:approximate dynamic programming, linear matrix inequalities, Q function, reinforcement learning, Takagi-Sugeno fuzzy modelsAutores:Henry Díaz, Jenyffer Yépez, Karla Paola NegreteFuentes:scopus