User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse




Book Chapter

Exploration from Generalization Mediated by Multiple Controllers

There are no MPG-Authors available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available

Dayan, P. (2013). Exploration from Generalization Mediated by Multiple Controllers. In G. Baldassarre, & M. Mirolli (Eds.), Intrinsically Motivated Learning in Natural and Artificial Systems (pp. 73-91). Berlin, Germany: Springer. doi:10.1007/978-3-642-32375-1_4.

Cite as: http://hdl.handle.net/21.11116/0000-0004-C2F1-0
Intrinsic motivation involves internally governed drives for exploration, curiosity, and play. These shape subjects over the course of development and beyond to explore to learn and expand the actions they are capable of performing and to acquire skills that can be useful in future domains. We adopt a utilitarian view of this learning process, treating it in terms of exploration bonuses that arise from distributions over the structure of the world that imply potential benefits from generalizing knowledge and skills to subsequent environments. We discuss how functionally and architecturally different controllers may realize these bonuses in different ways.