2013 | OriginalPaper | Buchkapitel
Emergence of Discrete and Abstract State Representation through Reinforcement Learning in a Continuous Input Task
verfasst von : Yoshito Sawatsubashi, Mohamad Faizal bin Samusudin, Katsunari Shibata
Erschienen in: Robot Intelligence Technology and Applications 2012
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
“Concept” is a kind of discrete and abstract state representation, and is considered useful for efficient action planning. However, it is supposed to emerge in our brain as a parallel processing and learning system through learning based on a variety of experiences, and so it is difficult to be developed by hand-coding. In this paper, as a previous step of the “concept formation”, it is investigated whether the discrete and abstract state representation is formed or not through learning in a task with multi-step state transitions using Actor-Q learning method and a recurrent neural network. After learning, an agent repeated a sequence two times, in which it pushed a button to open a door and moved to the next room, and finally arrived at the third room to get a reward. In two hidden neurons, discrete and abstract state representation not depending on the door opening pattern was observed. The result of another learning with two recurrent neural networks that are for Q-values and for Actors suggested that the state representation emerged to generate appropriate Q-values.