• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Mokymo pastiprinimu metodų pritaikymas kompiuterinio žaidimo personažui interaktyvioje 2D/3D grafikos sistemoje / An adaptation of reinforcement learning methods to the computer game character in interactive 2D/3D graphic system

Miliukas, Vaclovas 15 June 2011 (has links)
Šiame darbe buvo pasiūlyti dirbtinio intelekto pritaikymo būdai bei metodai, kompiuterinio žaidimo personažui, dviejų personažų koviniam žaidimui. Pasiūlytais būdais bei metodais buvo bandoma pritaikyti dirbtinį intelektą kompiuterinio žaidimo personažui, šio tipo žaidimui. Buvo tiriama ar pasliūlyti būdai ir metodai tinka šiai kompiuterinių žaidimų klasei. Taip pat buvo tiriamas agento mokymosi greitis, nuo ko jis priklauso bei ieškomi faktoriai, kurie lemia tokio tipo žaidimo personažams sparčiau mokintis ir naudingiau naudotis įgytomis žiniomis. Atrastus ir ištirtus faktorius buvo stengiamasi suderinti taip, kad mokomas personažas balansuotų tarp greitai besimokančio ir tinkamai besinaudojančio išmoktomis žiniomis. / In this work was offered an adjustments of techniques and methods of artificial intelligence for computer player, in two-players combat games. There was tried to adapt the artificial intelligence to the computer player, with those proposed techniques and methods in this type of games. Also was investigated whether those proposed techniques and methods suits for this class of computer games. In this work also was analyzed agent learning speed, on what depends it and explored the factors that determines the rapid learning speed and efficient use of agent knowledge. Discovered and investigated factors were fitted to the rapid learning speed and efficient use of agent knowledge.

Page generated in 0.0783 seconds