Uma Nova Metodologia para Avaliação de Desempenho de Algoritmos Baseados em Aprendizagem por Reforço

/in , , /by
Uma Nova Metodologia para Avaliação de Desempenho de Algoritmos Baseados em Aprendizagem por Reforço

Ribeiro, Richardson and Koerich, Alessandro L and Enembreck, Fabrício and Pós-graduação, Programa De and Aplicada, Informática

XXXIII Seminário Integrado de łdots 2006

Abstract : This paper presents a novel methodology to evaluate the performance of adaptive autonomous agents. Measuring the performance of a learning agent is not a trivial task and it generally requires lengthy simulations as well as knowledge about the domain. A generic łdots

You might also like
State-of-the-art retinal vessel segmentation with minimalistic models
Unified algorithm to improve reinforcement learning in dynamic environments an instance-based approach
Assessment of regional myocardial function via statistical features in MR images
Gender classification from unconstrained video sequences
Contextual object tracker with structure encoding
Experimental study of path planning problem using EMCOA for a holonomic mobile robot
Loss factors for learning Boosting ensembles from imbalanced data
Signature based Fuzzy Vaults with boosted feature selection