Skill acquisition through program-level imitation in a real-time domain

Publication Type  Journal Article
Year of Publication  2007
Authors  Wood, M. A.; Bryson, J. J.
Journal Title  IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume  37
Pagination  272-285
Key Words  Computer games; Program-level imitation; Representation; Social learning; algorithm; artificial intelligence; biomimetics; imitation; psychomotor performance; robotics; Algorithms; Imitative Behavior
Abstract  

This paper presents an imitation learning system capable of learning tasks in a complex dynamic real-time environment. In this paper, we argue that social learning should be thought of as a special case of general skill learning, and that the biases it presents to the skill learning problem radically simplify learning for species with sufficient innate predisposition to harness this power. We decompose skill learning into four subproblems, then show how a modification of Roy's CELL system can address all these problems simultaneously. Our system is demonstrated working in the domain of a real-time virtual-reality game, Unreal Tournament.

URL  http://www.cs.bath.ac.uk/~cspmaw/ieeesmcb.pdf

0

Free Registration

Registered users have the added benefit of being able to:

  • Search/filter the bibliography to find just the article you are looking for. You can search the computer games research bibliography by author, year, keyword, title or publication type.
  • Export references from the video games bibliography to a format suitable for your own work. Options currently include tagged and XML for Endnote users and BibTex for the rest of the world.
  • Post comments to discuss the paper or alert fellow researchers to other resources.
  • Add their own references using the 'create content' -> 'biblio' option in the block on the left.
  • NEW: Use the Biblio Search box located on the right hand of the page.
  • NEW: Browse by journal title, book title, author or keyword using the new Faceted Search tool.