Teaching Memoryless Randomized Learners Without Feedback

Abstract

The present paper mainly studies the expected teaching time of memoryless randomized learners without feedback. First, a characterization of optimal randomized learners is provided and, based on it, optimal teaching teaching times for certain classes are established. Second, the problem of determining the optimal teaching time is shown to be ${{\mathcal N\!P}}$ -hard. Third, an algorithm for approximating the optimal teaching time is given. Finally, two heuristics for teaching are studied, i.e., cyclic teachers and greedy teachers.

Cite

Text

Balbach and Zeugmann. "Teaching Memoryless Randomized Learners Without Feedback." International Conference on Algorithmic Learning Theory, 2006. doi:10.1007/11894841_11

Markdown

[Balbach and Zeugmann. "Teaching Memoryless Randomized Learners Without Feedback." International Conference on Algorithmic Learning Theory, 2006.](https://mlanthology.org/alt/2006/balbach2006alt-teaching/) doi:10.1007/11894841_11

BibTeX

@inproceedings{balbach2006alt-teaching,
  title     = {{Teaching Memoryless Randomized Learners Without Feedback}},
  author    = {Balbach, Frank J. and Zeugmann, Thomas},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2006},
  pages     = {93-108},
  doi       = {10.1007/11894841_11},
  url       = {https://mlanthology.org/alt/2006/balbach2006alt-teaching/}
}