| ID | 30121 |
| FullText URL | |
| Author | |
| Abstract | We propose herein a new incremental state construction method which consists of Fritzke's growing neural gas algorithm and a class management mechanism of GNG units. The GNG algorithm condenses sensory inputs and learns which areas are frequently sensed. The CMM yields a new state based upon the anticipated behaviors of the agent, i.e., a couple of actions by an agent and the resultant change in sensory inputs. Computational simulations on the mountain-car task confirm the effectiveness of the proposed method. |
| Keywords | learning (artificial intelligence)
neural nets
state-space methods
|
| Note | Digital Object Identifier: 10.1109/IJCNN.2004.1380090
Published with permission from the copyright holder. This is the institute's copy, as published in Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on, 25-29 July 2004, Vol. 2, Pages 1115-1120. Publisher URL:http://dx.doi.org/10.1109/IJCNN.2004.1380090 Copyright © 2004 IEEE. All rights reserved. |
| Published Date | 2004-7
|
| Publication Title |
Neural Networks
|
| Volume | volume2
|
| Start Page | 1115
|
| End Page | 1120
|
| Content Type |
Journal Article
|
| language |
English
|
| Refereed |
True
|
| DOI | |
| Submission Path | industrial_engineering/20
|
