| ID | 30083 |
| FullText URL | |
| Author |
Ninomiya, Akira
Horiuchi, Tadashi
Konishi, Tadataka
Baba, Mitsuru
|
| Abstract | In this paper, we propose a new incremental state segmentation method by utilizing information of the agents' state transition table which consists of a tuple of (state; action, state) in order to reduce the effort of designers and which is generated using the ART neural network. In the proposed method, if an inconsistent situation in the state transition table is observed, agents refine their map from perceptual inputs to states such that inconsistency is resolved. We introduce two kinds of inconsistency, i.e., different results caused by the same states and the same actions, and contradiction due to ambiguous states. Several computational simulations on cart-pole problems confirm the effectiveness of the proposed method |
| Keywords | ART neural nets
digital simulation
learning (artificial intelligence)
software agents
|
| Note | Digital Object Identifier: 10.1109/IECON.2000.972430
Published with permission from the copyright holder. This is the institute's copy, as published in Industrial Electronics Society, 2000. IECON 2000. 26th Annual Confjerence of the IEEE, 22-28 Oct. 2000, Vol. 4, Pages 2732-2737. Publisher URL:http://dx.doi.org/10.1109/IECON.2000.972430 Copyright © 2000 IEEE. All rights reserved. |
| Published Date | 2000-10
|
| Publication Title |
Industrial Electronics Society
|
| Volume | volume4
|
| Start Page | 2732
|
| End Page | 2737
|
| Content Type |
Journal Article
|
| language |
English
|
| Refereed |
True
|
| DOI | |
| Submission Path | industrial_engineering/42
|
