menu
{ "item_title" : "Evolutionary Artificial Neural Network Weight Tuning to Optimize Decision Making for an Abstract Game", "item_author" : [" Corey M. Miller "], "item_description" : "Abstract strategy games present a deterministic perfect information environment with which to test the strategic capabilities of artificial intelligence systems. With no unknowns or random elements, only the competitors' performances impact the results. This thesis takes one such game, Lines of Action, and attempts to develop a competitive heuristic. Due to the complexity of Lines of Action, artificial neural networks are utilized to model the relative values of board states. An application, pLoGANN (Parallel Lines of Action with Genetic Algorithm and Neural Networks), is developed to train the weights of this neural network by implementing a genetic algorithm over a distributed environment. While pLoGANN proved to be designed efficiently, it failed to produce a competitive Lines of Action player, shedding light on the difficulty of developing a neural network to model such a large and complex solution spa", "item_img_path" : "https://covers3.booksamillion.com/covers/bam/1/28/830/709/1288307098_b.jpg", "price_data" : { "retail_price" : "15.95", "online_price" : "15.95", "our_price" : "15.95", "club_price" : "15.95", "savings_pct" : "0", "savings_amt" : "0.00", "club_savings_pct" : "0", "club_savings_amt" : "0.00", "discount_pct" : "10", "store_price" : "" } }
Evolutionary Artificial Neural Network Weight Tuning to Optimize Decision Making for an Abstract Game|Corey M. Miller

Evolutionary Artificial Neural Network Weight Tuning to Optimize Decision Making for an Abstract Game

local_shippingShip to Me
In Stock.
FREE Shipping for Club Members help

Overview

Abstract strategy games present a deterministic perfect information environment with which to test the strategic capabilities of artificial intelligence systems. With no unknowns or random elements, only the competitors' performances impact the results. This thesis takes one such game, Lines of Action, and attempts to develop a competitive heuristic. Due to the complexity of Lines of Action, artificial neural networks are utilized to model the relative values of board states. An application, pLoGANN (Parallel Lines of Action with Genetic Algorithm and Neural Networks), is developed to train the weights of this neural network by implementing a genetic algorithm over a distributed environment. While pLoGANN proved to be designed efficiently, it failed to produce a competitive Lines of Action player, shedding light on the difficulty of developing a neural network to model such a large and complex solution spa

This item is Non-Returnable

Details

  • ISBN-13: 9781288307098
  • ISBN-10: 1288307098
  • Publisher: Biblioscholar
  • Publish Date: November 2012
  • Dimensions: 9.21 x 6.14 x 0.21 inches
  • Shipping Weight: 0.33 pounds
  • Page Count: 100

Related Categories

You May Also Like...

    1

BAM Customer Reviews