CHILD: A First Step Towards Continual Learning

Abstract

Continual learning is the constant development of increasingly complex behaviors; the process of building more complicated skills on top of those already developed. A continual-learning agent should therefore learn incrementally and hierarchically. This paper describes CHILD, an agent capable of Continual, Hierarchical, Incremental Learning and Development. CHILD can quickly solve complicated non-Markovian reinforcement-learning tasks and can then transfer its skills to similar but even more complicated tasks, learning these faster still.

Cite

Text

Ring. "CHILD: A First Step Towards Continual Learning." Machine Learning, 1997. doi:10.1023/A:1007331723572

Markdown

[Ring. "CHILD: A First Step Towards Continual Learning." Machine Learning, 1997.](https://mlanthology.org/mlj/1997/ring1997mlj-child/) doi:10.1023/A:1007331723572

BibTeX

@article{ring1997mlj-child,
  title     = {{CHILD: A First Step Towards Continual Learning}},
  author    = {Ring, Mark B.},
  journal   = {Machine Learning},
  year      = {1997},
  pages     = {77-104},
  doi       = {10.1023/A:1007331723572},
  volume    = {28},
  url       = {https://mlanthology.org/mlj/1997/ring1997mlj-child/}
}