Locally Weighted Learning for Control (1997)

Chris Atkeson Andrew Moore

Tags

Locally Weighted Learning, Markov Decision Processes, Reinforcement Learning

Abstract

Lazy learning methods provide useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of complex systems. This paper surveys ways in which locally weighted learning, a type of lazy learning, has been applied by us to control tasks. We explain various forms that control tasks can take, and how this affects the choice of learning paradigm. The discussion section explores the interesting impact that explicitly remembering all previous experiences has on the problem of learning to control.

Full text

Download (application/pdf, 834.5 kB)

Approximate BibTeX Entry

@article{atkeson-locally2,
    Month = {April},
    Year = {1997},
    Journal = {AI Review},
    Volume = {11},
    Pages = {75-113},
    Publisher = {Kluwer},
    Author = {Chris Atkeson Andrew Moore},
    Title = {Locally Weighted Learning for Control}
}