Piecemeal Learning of an Unknown Environment

Abstract

We introduce a new learning problem: learning a graph by piecemeal search , in which the learner must return every so often to its starting point (for refueling, say). We present two linear-time piecemeal-search algorithms for learning city-block graphs : grid graphs with rectangular obstacles.

Cite

Text

Betke et al. "Piecemeal Learning of an Unknown Environment." Machine Learning, 1995. doi:10.1007/BF00993411

Markdown

[Betke et al. "Piecemeal Learning of an Unknown Environment." Machine Learning, 1995.](https://mlanthology.org/mlj/1995/betke1995mlj-piecemeal/) doi:10.1007/BF00993411

BibTeX

@article{betke1995mlj-piecemeal,
  title     = {{Piecemeal Learning of an Unknown Environment}},
  author    = {Betke, Margrit and Rivest, Ronald L. and Singh, Mona},
  journal   = {Machine Learning},
  year      = {1995},
  pages     = {231-254},
  doi       = {10.1007/BF00993411},
  volume    = {18},
  url       = {https://mlanthology.org/mlj/1995/betke1995mlj-piecemeal/}
}