Robust Imitation of Diverse Behaviors

@inproceedings{Wang2017RobustIO,
  title={Robust Imitation of Diverse Behaviors},
  author={Ziyu Wang and Josh Merel and Scott E. Reed and Greg Wayne and Nando de Freitas and Nicolas Heess},
  booktitle={NIPS},
  year={2017}
}
Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascading failures when the agent trajectory diverges from the demonstrations. Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 56 times over the past 90 days. VIEW TWEETS
23 Citations
43 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 23 extracted citations

Similar Papers

Loading similar papers…