![](../pics/bar1.gif)
![Homepage](../pics/text1.gif)
![Research](../pics/text2.gif)
![Students](../pics/text3.gif)
![Courses](../pics/text4.gif)
![Robots](../pics/text5.gif)
![Papers](../pics/text6blue.gif)
![Videos](../pics/text7.gif)
![Press](../pics/text8.gif)
![Talks](../pics/text9.gif)
![Faq](../pics/text16.gif)
![CV](../pics/text10.gif)
![Lab](../pics/text11.gif)
![Travel](../pics/text15.gif)
![Contact](../pics/text12.gif)
![Personal](../pics/text13.gif)
![Links](../pics/text14.gif)
![](../pics/bar2.gif)
|
CHILD: A FIRST STEP TOWARDS CONTINUAL LEARNING
by Mark B. Ring
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.
|