Communication Dans Un Congrès Année : 2009

Um Mecanismo Construtivista para a Aprendizagem de Estrutura de MDPs Fatorados e Parcialmente Observáveis

Résumé

This paper presents CALM (Constructivist Anticipatory Learning Mechanism), an agent learning mechanism based on a constructivist approach of AI. It is designed to deal dynamically and interactively with environments which are at the same time partially deterministic and partially observable. We describe in detail the mechanism, explaining how the learning methods operate, and how it represents a world model using a factored MDP. We analyze the kinds of environmental regularities that CALM is able to discover, trying to show that our proposition follows the way towards the construction of more abstract or high-level representational concepts.
Fichier principal
Vignette du fichier
PEROTTO - ENIA 2009 (pre-print version).pdf (221) Télécharger le fichier
Loading...

Dates et versions

hal-01762257 , version 1 (17-04-2018)

Identifiants

  • HAL Id : hal-01762257 , version 1

Citer

Filipo Studzinski Perotto, Jean-Christophe Buisson, Luis Otávio Campos Alvares. Um Mecanismo Construtivista para a Aprendizagem de Estrutura de MDPs Fatorados e Parcialmente Observáveis. Congresso da Sociedade Brasileira de Computação (CSBC ENIA), Bento Gonçalves, RS, Brasil, 21/07/2009-24/07/2009, 2009, Porto Alegre, RS, Brazil. pp.1029--1038. ⟨hal-01762257⟩
67 Consultations
22 Téléchargements

Partager

More