Knows What It Knows: A Framework for Self-Aware Learning

Abstract

We introduce a learning framework that combines elements of the well-known PAC and mistake-bound models. The KWIK (knows what it knows) framework was designed particularly for its utility in learning settings where active exploration can impact the training examples the learner is exposed to, as is true in reinforcement-learning and active-learning problems. We catalog several KWIK-learnable classes and list some open problems in this area.

Cite

Text

Li et al. "Knows What It Knows: A Framework for Self-Aware Learning." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390228

Markdown

[Li et al. "Knows What It Knows: A Framework for Self-Aware Learning." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/li2008icml-knows/) doi:10.1145/1390156.1390228

BibTeX

@inproceedings{li2008icml-knows,
  title     = {{Knows What It Knows: A Framework for Self-Aware Learning}},
  author    = {Li, Lihong and Littman, Michael L. and Walsh, Thomas J.},
  booktitle = {International Conference on Machine Learning},
  year      = {2008},
  pages     = {568-575},
  doi       = {10.1145/1390156.1390228},
  url       = {https://mlanthology.org/icml/2008/li2008icml-knows/}
}