Cargando…
Learning a Set of Interrelated Tasks by Using a Succession of Motor Policies for a Socially Guided Intrinsically Motivated Learner
We aim at a robot capable to learn sequences of actions to achieve a field of complex tasks. In this paper, we are considering the learning of a set of interrelated complex tasks hierarchically organized. To learn this high-dimensional mapping between a continuous high-dimensional space of tasks and...
Autores principales: | Duminy, Nicolas, Nguyen, Sao Mai, Duhaut, Dominique |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6331524/ https://www.ncbi.nlm.nih.gov/pubmed/30670961 http://dx.doi.org/10.3389/fnbot.2018.00087 |
Ejemplares similares
-
Intrinsic motivation learning for real robot applications
por: Rayyes, Rania
Publicado: (2023) -
Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
por: Biehl, Martin, et al.
Publicado: (2018) -
Bootstrapping of Parameterized Skills Through Hybrid Optimization in Task and Policy Spaces
por: Queißer, Jeffrey F., et al.
Publicado: (2018) -
Dynamic Input Deep Learning Control of Artificial Avatars in a Multi-Agent Joint Motor Task
por: Lombardi, Maria, et al.
Publicado: (2021) -
Task Feasibility Maximization Using Model-Free Policy Search and Model-Based Whole-Body Control
por: Lober, Ryan, et al.
Publicado: (2020)