A synthesis of automated planning and reinforcement learning for efficient, robust decision-making

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,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Artificial intelligence Ročník 241; s. 103 - 130
Hlavní autoři: Leonetti, Matteo, Iocchi, Luca, Stone, Peter
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.12.2016
Elsevier Science Ltd
Témata:
Answer set programming
Approximation
Automated planning
Automation
Autonomous robot
Decision making
Decisions
Expert systems
Learning
Machine learning
Model accuracy
Reinforcement
Reinforcement learning
Reliability
Robot learning
Robots
Tasks
Autonomous robot
Robot learning
Automated planning
Answer set programming
Reinforcement learning
ISSN:0004-3702, 1872-7921
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0004-3702
1872-7921
DOI:10.1016/j.artint.2016.07.004