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.
Domaines
Intelligence artificielle [cs.AI]
Loading...