Explorative learning of inverse models: A theoretical perspective

@article{Rolf2014ExplorativeLO,
  title={Explorative learning of inverse models: A theoretical perspective},
  author={Matthias Rolf and Jochen J. Steil},
  journal={Neurocomputing},
  year={2014},
  volume={131},
  pages={2-14}
}
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… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-7 of 7 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 25 references

Failure of motor learning for large initial errors.

Neural computation • 2004
View 9 Excerpts
Highly Influenced

Bootstrapping intrinsically motivated learning with human demonstration

2011 IEEE International Conference on Development and Learning (ICDL) • 2011
View 1 Excerpt

Entry , exit , and diffusion with learning by doing

B. Jovanovic, S. Lach
IEEE Int . Joint Conf . Development and Learning and Epigenetic Robotics ( ICDLEpiRob ) • 2011

Online Goal Babbling for rapid bootstrapping of inverse models in high dimensions

2011 IEEE International Conference on Development and Learning (ICDL) • 2011
View 3 Excerpts

Goal Babbling Permits Direct Learning of Inverse Kinematics

IEEE Transactions on Autonomous Mental Development • 2010
View 10 Excerpts

Intrinsically motivated goal exploration for active motor learning in robots: A case study

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems • 2010
View 1 Excerpt

Oudeyer , Intrinsically motivated goal exploration for active motor learning in robots : A case study

P.-Y.
IEEE / RSJ Int . Conf . Intelligent Robots and Systems ( IROS ) • 2010

Efficient exploration and learning of whole body kinematics

2009 IEEE 8th International Conference on Development and Learning • 2009
View 1 Excerpt

Similar Papers

Loading similar papers…