| Files: | Description | File size | Format | Browse |
| Fulltext | 0.24 MB | PDF (requires Acrobat Reader) | Previous | Next |
| PostScript | | | |
| | |
| Authors: | Marius Oancea: Universitatii Lucian Blaga, Sibiu, Romania |
| | Ciprian Candea: Universitatii Lucian Blaga, Sibiu, Romania |
| | Daniel Volovici: Universitatii Lucian Blaga, Sibiu, Romania |
| Publication title: | SibiuTeam Team |
| Conference: | RobocCup-99 Team Descriptions. Simulation League |
| Publication type: | Abstract and Fulltext |
| Issue: | 004 |
| Article No.: | 031 |
| Abstract: | We use simulated soccer to study multi-agent learning. Each team member tries to learn from the corresponding human player in a real game. Following a unified approach, strategic and tactical behavior is learned synergistically by training a feed-forward neural network (ANN) with a modified back-propagation algorithm. It aims at decreasing the learning time and avoiding the local maximums. We tried to minimize the computation effort, as required in classic back-propagation (BKP) methods. |
| Language: | English |
| Year: | 1999 |
| No. of pages: | 5 |
| Pages: | 139-143 |
| Series: | Linköping Electronic Conference Proceedings |
| ISSN (print): | 1650-3686 |
| ISSN (online): | 1650-3740 |
| File: | http://www.ep.liu.se/ea/cis/1999/007/31/cis9900731.pdf |
| Available: | 1999-12-15 |
| Publisher: | Linköping University Electronic Press, Linköpings universitet |
|
| REFERENCE TO THIS PAGE |
Ph.D., Lic. Theses
