Explorative Learning of Inverse Models: a Theoretical Perspective

Rolf M, Steil JJ (2014)
Neurocomputing 131(Special Issue: New Challenges in Neural Computation): 2-14.

Journal Article | Published | English

No fulltext has been uploaded

Abstract
We investigate the role of redundancy for exploratory learning of inverse functions, where an agent learns to achieve goals by performing actions and observing outcomes. We present an analysis of linear redundancy and investigate goal-directed exploration approaches, which are empirically successful, but hardly theorized except negative results for special cases, and prove convergence to the optimal solution. We show that the learning curves of such processes are intrinsically low-dimensional and S-shaped, which explains previous empirical findings, and finally compare our results to non-linear domains.
Publishing Year
ISSN
PUB-ID

Cite this

Rolf M, Steil JJ. Explorative Learning of Inverse Models: a Theoretical Perspective. Neurocomputing. 2014;131(Special Issue: New Challenges in Neural Computation):2-14.
Rolf, M., & Steil, J. J. (2014). Explorative Learning of Inverse Models: a Theoretical Perspective. Neurocomputing, 131(Special Issue: New Challenges in Neural Computation), 2-14.
Rolf, M., and Steil, J. J. (2014). Explorative Learning of Inverse Models: a Theoretical Perspective. Neurocomputing 131, 2-14.
Rolf, M., & Steil, J.J., 2014. Explorative Learning of Inverse Models: a Theoretical Perspective. Neurocomputing, 131(Special Issue: New Challenges in Neural Computation), p 2-14.
M. Rolf and J.J. Steil, “Explorative Learning of Inverse Models: a Theoretical Perspective”, Neurocomputing, vol. 131, 2014, pp. 2-14.
Rolf, M., Steil, J.J.: Explorative Learning of Inverse Models: a Theoretical Perspective. Neurocomputing. 131, 2-14 (2014).
Rolf, Matthias, and Steil, Jochen J. “Explorative Learning of Inverse Models: a Theoretical Perspective”. Neurocomputing 131.Special Issue: New Challenges in Neural Computation (2014): 2-14.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Search this title in

Google Scholar