An Enactive Approach to Autonomous Agent and Robot Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

An Enactive Approach to Autonomous Agent and Robot Learning

Abstract

A novel way to model autonomous learning in artificial agents and robots is introduced, called an Enactive Markov Decision Process (EMDP). An EMDP keeps perception and action embedded within sensorimotor schemes rather than dissociated. On each decision cycle, the agent tries to enact a sensorimotor scheme, and the environment informs the agent whether it was indeed enacted or whether another sensorimotor scheme was enacted instead. This new modeling approach leads to implementing a new form of self-motivation called interactional motivation. An EMDP learning algorithm is presented. Results show that this algorithm allows the agent to develop active perception as it learns to master the sensorimotor contingences afforded by its coupling with the environment.
Fichier principal
Vignette du fichier
GeorgeonO-Epirob2013.pdf (2.52 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01339220 , version 1 (20-10-2016)

Identifiers

Cite

Olivier L. Georgeon, Christian Wolf, Simon Gay. An Enactive Approach to Autonomous Agent and Robot Learning. Joint International Conference on Development and Learning and on Epigenetic Robotics, Aug 2013, Osaka, Japan. pp.1-6, ⟨10.1109/DevLrn.2013.6652527⟩. ⟨hal-01339220⟩
214 View
102 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More