Title :
Temporal Difference Learning of an Othello Evaluation Function for a Small Neural Network with Shared Weights
Author :
Manning, Edward P.
Author_Institution :
Brookdale Community Coll., Lincroft, NJ
Abstract :
This paper presents an artificial neural network with shared weights, trained to play the game of Othello by self-play with temporal difference learning (TDL). The network performs as well as the champion of the CEC 2006 Othello Evaluation Function Competition. The TDL-trained network contains only 67 unique weights compared to 2113 for the champion
Keywords :
computer games; learning (artificial intelligence); neural nets; Othello evaluation function; artificial neural network; self-play; temporal difference learning; Artificial neural networks; Computational intelligence; Educational institutions; Humans; Law; Legal factors; Neural networks; Performance evaluation; State-space methods; USA Councils; Othello; neural network; shared weights; temporal difference learning;
Conference_Titel :
Computational Intelligence and Games, 2007. CIG 2007. IEEE Symposium on
Conference_Location :
Honolulu, HI
Print_ISBN :
1-4244-0709-5
DOI :
10.1109/CIG.2007.368101
