posted on 2009-01-01, 00:00authored byJonathan Mugan, Benjamin Kuipers
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.