Relational Reinforcement Learning for Planning with Exogenous Effects - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Machine Learning Research Année : 2017

Relational Reinforcement Learning for Planning with Exogenous Effects

Résumé

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 generation of candidate models, with an optimization method to select the best set of planning operators to model a problem. We also show how to combine this learner with reinforcement learning algorithms to solve complete problems. Finally, experimental validation is provided that shows improvements over previous work in both simulation and a robotic task. The robotic task involves a dynamic scenario with several agents where a manipulator robot has to clear the tableware on a table. We show that the exogenous effects learned by our approach allowed the robot to clear the table in a more efficient way.
Fichier principal
Vignette du fichier
16-326.pdf (2.24 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01710491 , version 1 (16-02-2018)

Licence

Paternité

Identifiants

  • HAL Id : hal-01710491 , version 1

Citer

David Martinez, Guillem Alenya, Tony Ribeiro, Katsumi Inoue, Carme Torras. Relational Reinforcement Learning for Planning with Exogenous Effects. Journal of Machine Learning Research, 2017, 18, pp.1 - 44. ⟨hal-01710491⟩
311 Consultations
27 Téléchargements

Partager

Gmail Facebook X LinkedIn More