Dissertation/Thesis Abstract

Application of temporal difference learning to the game of Snake
by Lockhart, Christopher, M.Eng., University of Louisville, 2010, 96; 1485160
Abstract (Summary)

The game of Snake has been selected to provide a unique application of the TD(λ) algorithm as proposed by Sutton. A reinforcement learning technique for producing computer controlled players is documented. Using value function approximation with multilayer artificial neural networks and the actor-critic architecture, computer players capable of playing the game of Snake can be created. The adaptation to the standard neural network backpropagation procedure will be documented. Not only does the proposed technique provide reasonable player performance, its application is unique; this approach to Snake has never been documented. By performing sets of trials, the performance of the players are evaluated and compared against an existing machine learning technique. Learning curves provide visualization for the results. Though the snake players are shown to be capable of achieving lower scores than with the existing method, the technique is able to produce agents that accumulate scores, much more efficiently.

Indexing (document details)
Advisor: Desoky, Ahmed
Commitee:
School: University of Louisville
School Location: United States -- Kentucky
Source: MAI 48/06M, Masters Abstracts International
Source Type: DISSERTATION
Subjects: Computer Engineering, Computer science
Keywords:
Publication Number: 1485160
ISBN: 9781124102832
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest