Causal Learnability

Michael, Loizos

doi:10.5591/978-1-57735-516-8/IJCAI11-174

Causal Learnability

Loizos Michael

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1014-1019.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-174

Abstract

The ability to predict, or at least recognize, the state of the world that an action brings about, is a central feature of autonomous agents. We propose, herein, a formal framework within which we investigate whether this ability can be autonomously learned. The framework makes explicit certain premises that we contend are central in such a learning task: (i) slow sensors may prevent the sensing of an action's direct effects during learning; (ii) predictions need to be made reliably in future and novel situations. We initiate in this work a thorough investigation of the conditions under which learning is or is not feasible. Despite the very strong negative learnability results that we obtain, we also identify interesting special cases where learning is feasible and useful.

Loizos Michael. 2011. Causal Learnability. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 1014–1019. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-174

@inproceedings{ijcai2011p174,
  title     = {Causal Learnability},
  author    = {Michael, Loizos},
  booktitle = {Proceedings of the Twenty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-11}},
  publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
  editor    = {Toby Walsh},
  pages     = {1014--1019},
  year      = {2011},
  month     = {7},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-174},
  url       = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-174},
}

TY  - CPAPER
TI  - Causal Learnability
AU  - Michael, Loizos
T2  - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11
PB  - AAAI Press/International Joint Conferences on Artificial Intelligence
PY  - 2011
SP  - 1014
EP  - 1019
DO  - 10.5591/978-1-57735-516-8/IJCAI11-174
UR  - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-174
ER  -