Maximizing Learning Progress: An Internal Reward System for Development

@inproceedings{Kaplan2003MaximizingLP,
  title={Maximizing Learning Progress: An Internal Reward System for Development},
  author={Fr{\'e}d{\'e}ric Kaplan and Pierre-Yves Oudeyer},
  booktitle={Embodied Artificial Intelligence},
  year={2003}
}
This chapter presents a generic internal reward system that drives an agent to increase the complexity of its behavior. This reward system does not reinforce a predefined task. Its purpose is to drive the agent to progress in learning given its embodiment and the environment in which it is placed. The dynamics created by such a system are studied first in a simple environment and then in the context of active vision. 
Highly Cited
This paper has 79 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
51 Citations
21 References
Similar Papers

Citations

Publications citing this paper.

79 Citations

0510'05'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 79 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Robot bouncing : On the interaction between body and environmental dynamics

  • M. Lungarella, L. Berthouze
  • this volume
  • 2004
1 Excerpt

Proceedings of the 3 rd international workshop on Epigenetic Robotics : Modeling cognitive development in robotic systems

  • C. Prince, L. Berthouze, H. Kozima, D. Bullock, G. Stojanov, C. Balkenius
  • 2003

An evolutionary active-vision system

  • T. Kato, D. Floreano
  • Proceedings of the congress on evolutionary…
  • 2001
1 Excerpt

Similar Papers

Loading similar papers…