Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Relational reinforcement learning with guided demonstrations

Autor
Martínez, D.; Alenyà, G.; Torras, C.
Tipus d'activitat
Article en revista
Revista
Artificial intelligence
Data de publicació
2017
Volum
247
Pàgina inicial
295
Pàgina final
312
DOI
https://doi.org/10.1016/j.artint.2015.02.006 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/113084 Obrir en finestra nova
URL
http://www.sciencedirect.com/science/article/pii/S0004370215000284?via%3Dihub Obrir en finestra nova
Resum
Model-based reinforcement learning is a powerful paradigm for learning tasks in robotics. However, in-depth exploration is usually required and the actions have to be known in advance. Thus, we propose a novel algorithm that integrates the option of requesting teacher demonstrations to learn new domains with fewer action executions and no previous knowledge. Demonstrations allow new actions to be learned and they greatly reduce the amount of exploration required, but they are only requested when...
Citació
Martínez, D., Alenyà, G., Torras, C. Relational reinforcement learning with guided demonstrations. "Artificial intelligence", 2017, vol. 247, p. 295-312.
Paraules clau
active learning, generalisation (artificial intelligence), human-robot interaction, learning (artificial intelligence), manipulators, model-based reinforcement learning, uncertainty handling
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI

Participants