Találati lista | Tudóstér

001-es BibID:	BIBFORM044019
Első szerző:	Fülöp András (informatikus)
Cím:	Virtual Military Robot Controlled by Emotical Agents Using Reinforcement Learning / András Fülöp, Márton Ispány
Dátum:	2010
Megjegyzések:	Remote controlled and (later) intelligence driven military devices have been existed for a long time. Probably, in the wars of the future robots will fight each other instead of soldiers, avoiding human casulties. An abstract view of the tank's battles is the Jrobots competition, in which two or more virtual tanks fight against each other. These virtual robots are programmed in advance (in Java language) using built in heuristics in order to win. However,these programmed artificial intelligencies can be exceeded by machine learning methods. In this talk we introduce an emotical agent which learns the optimal strategy and therefore the optimal emotion, using a reinforcement learning method called SARSA(?). Using three different behaviors - called emotions - which are pre-programmed basic heuristics, the agent can defeat a more complex artifical agent (which defeated the behaviors one by one).
ISBN:	978 963 9894 72 3
Tárgyszavak:	Természettudományok Matematika- és számítástudományok előadáskivonat könyvrészlet Reinforcement Learning SARSA(?) Emotical agent Neurotic agent JRobots Artificial Intelligence
Megjelenés:	Proceedings of the 8th International Conference on Applied Informatics : Eger, Hungary, January 27 - 30, 2010. vol. 1. / ed. Attila Egri-Nagy [et al.]. - p. 71-77. -
További szerzők:	Ispány Márton (1966-) (informatikus, matematikus)
Internet cím:	Szerző által megadott URL Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: