Download PDFOpen PDF in browser

When Should Learning Agents Switch to Explicit Knowledge?

13 pagesPublished: September 29, 2016

Abstract

According to psychological models, learned knowledge can be distinguished into implicit and explicit knowledge. The former can be exploited, but cannot be verbalized easily (e.\,g., to explain it to another person). The latter is available in an explicit form, it often comprises generalized, rule-based knowledge which can be verbalized and explained to others. During a learning process, the learned knowledge starts in an implicit form and gets explicit as the learning process progresses, and humans benefit from exploiting such generalized, rule-based knowledge when learning. This paper investigates how learning agents can benefit from explicit knowledge which is extracted during a learning process from a learned implicit representation. It is clearly shown that an agent can already benefit from explicit knowledge in early phases of a learning process.

Keyphrases: knowledge extraction, learning agents, symbolic/sub-symbolic integration

In: Christoph Benzmüller, Geoff Sutcliffe and Raul Rojas (editors). GCAI 2016. 2nd Global Conference on Artificial Intelligence, vol 41, pages 174--186

Links:
BibTeX entry
@inproceedings{GCAI2016:When_Should_Learning_Agents,
  author    = {Daan Apeldoorn and Gabriele Kern-Isberner},
  title     = {When Should Learning Agents Switch to Explicit Knowledge?},
  booktitle = {GCAI 2016. 2nd Global Conference on Artificial Intelligence},
  editor    = {Christoph Benzm\textbackslash{}"uller and Geoff Sutcliffe and Raul Rojas},
  series    = {EPiC Series in Computing},
  volume    = {41},
  pages     = {174--186},
  year      = {2016},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/xrz},
  doi       = {10.29007/2bgs}}
Download PDFOpen PDF in browser