ML Anthology

Formal Theory of Fun and Creativity

Jürgen Schmidhuber
ECML-PKDD 2010 pp. 6
doi:10.1007/978-3-642-15880-3_6 /ecmlpkdd/2010/schmidhuber2010ecmlpkdd-formal/

Abstract

To build a creative agent that never stops generating non-trivial & novel & surprising data, we need two learning modules: (1) an adaptive predictor or compressor or model of the growing data history as the agent is interacting with its environment, and (2) a general reinforcement learner. The LEARNING PROGRESS of (1) is the FUN or intrinsic reward of (2). That is, (2) is motivated to invent interesting things that (1) does not yet know but can easily learn.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Schmidhuber. "Formal Theory of Fun and Creativity." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2010. doi:10.1007/978-3-642-15880-3_6

Markdown

[Schmidhuber. "Formal Theory of Fun and Creativity." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2010.](https://mlanthology.org/ecmlpkdd/2010/schmidhuber2010ecmlpkdd-formal/) doi:10.1007/978-3-642-15880-3_6

BibTeX

@inproceedings{schmidhuber2010ecmlpkdd-formal,
  title     = {{Formal Theory of Fun and Creativity}},
  author    = {Schmidhuber, Jürgen},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2010},
  pages     = {6},
  doi       = {10.1007/978-3-642-15880-3_6},
  url       = {https://mlanthology.org/ecmlpkdd/2010/schmidhuber2010ecmlpkdd-formal/}
}