Title :
Efficient learning by symbol emergence in multilayer network and agent collaboration
Author :
Tano, S. ; Futamura, D. ; Uemura, Y.
Author_Institution :
Graduate Sch. of Inf. Syst., Univ. of Electro-Commun., Tokyo, Japan
Abstract :
Two simple models, Model-A and Model-B, are described as the first step toward fusing computational and symbolic processing. Model-B is an extension of the Model-A. Each of them consists of two layers. The lower layer is a neural network in which Q-learning is simulated. The inputs are the state variables, and the outputs are the Q-values for each action. It is tuned to update and store the Q-table. The upper layer watches the activity in the lower layer to identify the group of nodes that are activated when some action in the lower layer obtains a high reward from the environment. In this way, new symbols emerge that are embedded in the lower layer to speed up the learning. Model-B is extended so as to learn more complex concepts quickly. When an important concept is learned, the corresponding symbol is generalized and embedded in a different place at a lower level. Simulation demonstrated that symbol emergence and the forced application of these symbols in Q-learning greatly improves the performance of players playing a simple football game
Keywords :
feedforward neural nets; hierarchical systems; learning (artificial intelligence); multi-agent systems; multimedia computing; sensor fusion; symbol manipulation; Q-learning; agent collaboration; deep fusion; hierarchical systems; multilayer neural network; multimedia computing; symbol emergence; Collaboration; Computational intelligence; Computational modeling; Computer architecture; Computer networks; Hierarchical systems; Intelligent networks; Intelligent systems; Neural networks; Watches;
Conference_Titel :
Fuzzy Systems, 2000. FUZZ IEEE 2000. The Ninth IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-5877-5
DOI :
10.1109/FUZZY.2000.839198