Analysing the Difficulty of Learning Goal-Scoring Behaviour for Robot Soccer - PDF

Analysing the Difficulty of Learning Goal-Scoring Behaviour for Robot Soccer
A brief insight on a method for the analysis of the fitness landscape described by the problem of learning goal-scoring behaviour for robot soccer – a problem that is considered to be very difficult for evolutionary algorithms. The method described uses landscape measures to examine features of the fitness landscape such as the degree of correlation between, or randomness of, points on the landscape, the modality of the landscape, and the ruggedness of the landscape.
This is only PDF preview of first few pages of Analysing the Difficulty of Learning Goal-Scoring Behaviour for Robot Soccer by Jeff Riley, Vic Ciesielski. Please download the full version to read the complete book.
Note: You must have Adobe Reader or Acrobat Installed to see this Preview
You currently don't have Adobe Reader installed. In order to view this file, please download Adobe Reader from <a href="https://get.adobe.com/reader/" target="_blank">here</a>. Or, if you want to download the PDF file to your computer, please click <a href="https://www.free-ebooks.net/ebook/Analysing-the-Difficulty-of-Learning-Goal-Scoring-Behaviour-for-Robot-Soccer/pdf">here</a>.