Preference-Based Policy Learning

@inproceedings{Akrour2011PreferenceBasedPL,
  title={Preference-Based Policy Learning},
  author={Riad Akrour and Marc Schoenauer and Mich{\`e}le Sebag},
  booktitle={ECML/PKDD},
  year={2011}
}
Many machine learning approaches in robotics, based on reinforcement learning, inverse optimal control or direct policy learning, critically rely on robot simulators. This paper investigates a simulatorfree direct policy learning, called Preference-based Policy Learning (PPL). PPL iterates a four-step process: the robot demonstrates a candidate policy; the expert ranks this policy comparatively to other ones according to her preferences; these preferences are used to learn a policy return… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 42 CITATIONS

Combining fitness-based search and user modeling in evolutionary robotics

VIEW 10 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Renforcements naturels pour la collaboration homme-machine

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Collective Design of Robot Locomotion

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 30 REFERENCES

Reinforcement Learning: An Introduction

  • IEEE Transactions on Neural Networks
  • 1988
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

On Learning, Representing, and Generalizing a Task in a Humanoid Robot

  • IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2007
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…