Title :
Evolutionary constitution of game player agents
Author :
Handa, Hiroyuki ; Horiuchi, T.
Author_Institution :
Okayama Univ., Japan
Abstract :
In this paper, we propose a constitution method of game player agent that adopts a neural network as a state evaluation function for the game player, and evolves its weights and structure by evolutionary strategy. In this method, we attempt to acquire a better state evaluation function by evolving weights and structure simultaneously.
Keywords :
games of skill; genetic algorithms; neural nets; software agents; complete-information games; evolutionary computations; game player agent; game-playing programs; neural network; state evaluation function; Artificial intelligence; Classification tree analysis; Constitution; Educational institutions; Evolutionary computation; Function approximation; Genetic mutations; Learning; Neural networks;
Conference_Titel :
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN :
0-7803-7631-5
DOI :
10.1109/SICE.2002.1196552
