An autonomous explore/exploit strategy

@inproceedings{McMahon2005AnAE,
  title={An autonomous explore/exploit strategy},
  author={Alex McMahon and Dan Scott and William N. L. Browne},
  booktitle={GECCO Workshops},
  year={2005}
}
In reinforcement learning problems it has been considered that neither exploitation nor exploration can be pursued exclusively without failing at the task. The optimal balance between exploring and exploiting changes as the training progresses due to the increasing amount of learnt knowledge. This shift in balance is not known a priori so an autonomous online adjustment is sought. Human beings manage this balance through logic and explorations based on feedback from the environment. The XCS… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-5 of 5 references

Anticipatory Learning Classifier Systems

Genetic Algorithms and Evolutionary Computation • 2002
View 5 Excerpts
Highly Influenced

Explore/Exploit Strategies in Auton omy

S. Wilson
From Animals to Animats 4. Proceedings of the Fourth International Conference on Simulation of Adaptive Behaviour, • 1996
View 8 Excerpts
Highly Influenced

Adaptation’, in Progress in the or

J. H. Holland
tical biology, • 1976
View 10 Excerpts
Highly Influenced

Précis of The brain and emotion.

The Behavioral and brain sciences • 2000
View 3 Excerpts
Highly Influenced

Plenary Lecture ‘Representation, Search and Learning.

L. D. Whitley
Abstract Proc 3rd Int. Conf. on Artificial Neural Networks and Geneti c Algorithms (ICANNGA97), • 1997
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…