Skip to Main content Skip to Navigation
Theses

Un Mécanisme Constructiviste d'Apprentissage Automatique d'Anticipations pour des Agents Artificiels Situés

Abstract : This research is characterized, first, by a theoretical discussion on the concept of autonomous agent, based on elements taken from the Situated AI and the Affective AI paradigms. Secondly, this thesis presents the problem of learning world models, providing a bibliographic review regarding some related works. From these discussions, the CAES architecture and the CALM mechanism are presented. The CAES (Coupled Agent-Environment System) is an architecture for describing systems based on the agent-environment dichotomy. It defines the agent and the environment as two partially open systems, in dynamic coupling. The agent is composed of two sub-systems, mind and body, following the principles of situativity and intrinsic motivation. CALM (Constructivist Learning Anticipatory Mechanism) is based on the constructivist approach to Artificial Intelligence. It allows a situated agent to build a model of the world in environments partially deterministic and partially observable in the form of Partially Observable and Factored Markov Decision Process (FPOMDP). The model of the world is constructed and used for the agent to define a policy for action in order to improve its own performance.
Document type :
Theses
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-00620755
Contributor : Filipo Studzinski Perotto <>
Submitted on : Thursday, September 8, 2011 - 3:58:10 PM
Last modification on : Tuesday, September 8, 2020 - 10:00:06 AM
Long-term archiving on: : Friday, December 9, 2011 - 2:25:43 AM

Identifiers

  • HAL Id : tel-00620755, version 1

Collections

Citation

Filipo Studzinski Perotto. Un Mécanisme Constructiviste d'Apprentissage Automatique d'Anticipations pour des Agents Artificiels Situés. Informatique [cs]. Institut National Polytechnique de Toulouse - INPT, 2010. Français. ⟨tel-00620755⟩

Share

Metrics

Record views

471

Files downloads

2918