Automated planning and reinforcement learning are characterized by complementary views on decision making: the former relies on previous knowledge and computation, while the latter on interaction with the world, and experience. Planning allows robots to carry out different tasks in the same domain, without the need to acquire knowledge about each one of them, but relies strongly on the accuracy of the model. Reinforcement learning, on the other hand, does not require previous knowledge, and allows robots to robustly adapt to the environment, but often necessitates an infeasible amount of experience. We present Domain Approximation for Reinforcement LearnING (DARLING), a method that takes advantage of planning to constrain the behavior of the agent to reasonable choices, and of reinforcement learning to adapt to the environment, and increase the reliability of the decision making process. We demonstrate the effectiveness of the proposed method on a service robot, carrying out a variety of tasks in an office building. We find that when the robot makes decisions by planning alone on a given model it often fails, and when it makes decisions by reinforcement learning alone it often cannot complete its tasks in a reasonable amount of time. When employing DARLING, even when seeded with the same model that was used for planning alone, however, the robot can quickly learn a behavior to carry out all the tasks, improves over time, and adapts to the environment as it changes.
A synthesis of automated planning and reinforcement learning for efficient, robust decision-making / Leonetti, Matteo; Iocchi, Luca; Stone, Peter. - In: ARTIFICIAL INTELLIGENCE. - ISSN 0004-3702. - STAMPA. - 241:(2016), pp. 103-130. [10.1016/j.artint.2016.07.004]
A synthesis of automated planning and reinforcement learning for efficient, robust decision-making
LEONETTI, MATTEO
;IOCCHI, Luca
;
2016
Abstract
Automated planning and reinforcement learning are characterized by complementary views on decision making: the former relies on previous knowledge and computation, while the latter on interaction with the world, and experience. Planning allows robots to carry out different tasks in the same domain, without the need to acquire knowledge about each one of them, but relies strongly on the accuracy of the model. Reinforcement learning, on the other hand, does not require previous knowledge, and allows robots to robustly adapt to the environment, but often necessitates an infeasible amount of experience. We present Domain Approximation for Reinforcement LearnING (DARLING), a method that takes advantage of planning to constrain the behavior of the agent to reasonable choices, and of reinforcement learning to adapt to the environment, and increase the reliability of the decision making process. We demonstrate the effectiveness of the proposed method on a service robot, carrying out a variety of tasks in an office building. We find that when the robot makes decisions by planning alone on a given model it often fails, and when it makes decisions by reinforcement learning alone it often cannot complete its tasks in a reasonable amount of time. When employing DARLING, even when seeded with the same model that was used for planning alone, however, the robot can quickly learn a behavior to carry out all the tasks, improves over time, and adapts to the environment as it changes.File | Dimensione | Formato | |
---|---|---|---|
Leonetti_Preprint-A-synthesis_2016.pdf
accesso aperto
Tipologia:
Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza:
Creative commons
Dimensione
3.31 MB
Formato
Adobe PDF
|
3.31 MB | Adobe PDF | |
Leonetti_A-synthesis_2016.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
3.57 MB
Formato
Adobe PDF
|
3.57 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.