One-Shot Imitation Learning

@inproceedings{Duan2017OneShotIL,
  title={One-Shot Imitation Learning},
  author={Yan Duan and Marcin Andrychowicz and Bradly C. Stadie and Jonathan Ho and Jonas Schneider and Ilya Sutskever and Pieter Abbeel and Wojciech Zaremba},
  booktitle={NIPS},
  year={2017}
}
Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 138 CITATIONS

Learning Invariances for Policy Generalization

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration

VIEW 10 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

  • ICLR
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Overcoming Exploration in Reinforcement Learning with Demonstrations

  • 2018 IEEE International Conference on Robotics and Automation (ICRA)
  • 2017
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

  • ArXiv
  • 2019
VIEW 6 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Adversarial Task Transfer from Preference

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

An Algorithmic Perspective on Imitation Learning

  • Foundations and Trends in Robotics
  • 2018
VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 12 Highly Influenced Citations

  • Averaged 46 Citations per year from 2017 through 2019

References

Publications referenced by this paper.