Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Relational reinforcement learning for planning with exogenous effects

Autor
Martinez, D.; Alenyà, G.; Ribeiro, T.; Inoue, K.; Torras, C.
Tipus d'activitat
Article en revista
Revista
Journal of machine learning research
Data de publicació
2017
Volum
18
Número
78
Pàgina inicial
1
Pàgina final
44
Projecte finançador
Robots Understanding Their Actions by Imagining Their Effects
TIN2014-58178-R Instructing robots using natural communication skills National Project
Repositori
http://hdl.handle.net/2117/113085 Obrir en finestra nova
URL
http://jmlr.org/papers/volume18/16-326/16-326.pdf Obrir en finestra nova
Resum
Probabilistic planners have improved recently to the point that they can solve difficult tasks with complex and expressive models. In contrast, learners cannot tackle yet the expressive models that planners do, which forces complex models to be mostly handcrafted. We propose a new learning approach that can learn relational probabilistic models with both action effects and exogenous effects. The proposed learning approach combines a multi-valued variant of inductive logic programming for the gen...
Citació
Martinez, D., Alenyà, G., Ribeiro, T., Inoue, K., Torras, C. Relational reinforcement learning for planning with exogenous effects. "Journal of machine learning research", 2017, vol. 18, núm. 78, p. 1-44.
Paraules clau
Active Learning, Learning Models for Planning, Model-Based RL, Probabilistic Planning, Robot Learning
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI

Participants