Autor: |
Sree, P. Kiran, Raju, G. V. S., Raju, S. Viswandha, Devi, N. S. S. S. N Usha |
Rok vydání: |
2013 |
Předmět: |
|
Zdroj: |
Artificial Intelligence and Machine Learning Journal(ICGST-AIML), Volume 8, Issue I, June 2008,pp 29-37 |
Druh dokumentu: |
Working Paper |
Popis: |
This paper reports on the application of sequence analysis algorithms for agents in robotic soccer and a suitable representation is proposed to achieve this mapping. The objective of this research is to generate novel better in-game strategies with the aim of faster adaptation to the changing environment. A homogeneous non-communicating multi-agent architecture using the representation is presented. To achieve real-time learning during a game, a bucket brigade algorithm is used to reinforce Cellular Automata Based Classifier. A technique for selecting strategies based on sequence analysis is adopted. |
Databáze: |
arXiv |
Externí odkaz: |
|