Batch Active Preference-Based Learning of Reward Functions

@inproceedings{Biyik2018BatchAP,
  title={Batch Active Preference-Based Learning of Reward Functions},
  author={Erdem Biyik and Dorsa Sadigh},
  booktitle={CoRL},
  year={2018}
}
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by querying users with preference questions. In this paper, we will develop a new algorithm, batch active preference-based learning, that enables efficient learning of reward functions using as few data samples as possible while still having short query… CONTINUE READING
9
Twitter Mentions

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

Influencing Leading and Following in Human-Robot Teams

Minae Kwon, Mengxi Li, Alexandre Bucquet, Dorsa Sadigh
  • 2019
VIEW 1 EXCERPT

References

Publications referenced by this paper.
SHOWING 1-10 OF 44 REFERENCES

OpenAI Gym

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Do You Want Your Autonomous Car to Drive Like You?

  • 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI
  • 2017
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…