Action Acquisition in QLAP

DMCA

Action Acquisition in QLAP

Cached

by Jonathan Mugan , Benjamin Kuipers , Jonathan Mugan , Benjamin Kuipers

BibTeX

@MISC{Mugan_actionacquisition,
    author = {Jonathan Mugan and Benjamin Kuipers and Jonathan Mugan and Benjamin Kuipers},
    title = {Action Acquisition in QLAP},
    year = {}
}

OpenURL

Abstract

An important part of development is acquiring actions to interact with the environment. We have developed a computational model of autonomous action acquisition, called QLAP. In this paper we investigate different strategies for developmental action acquisition within this model. In particular, we introduce a way to actively learn actions and we compare this active action acquisition with passive learning of actions. We also compare curiosity based exploration with random exploration. And finally, we examine the effects of resource restrictions on the agent’s ability to learn actions. 1.

Keyphrases

action acquisition different strategy important part agent ability random exploration autonomous action acquisition passive learning active action acquisition computational model resource restriction developmental action acquisition

DMCA