Generative Adversarial Imitation Learning ​

← Back to topic

Authors: Jonathan Ho, Stefano Ermon
Year: 2017
Journal: NeurIPS
DOI: 10.48550/arXiv.1606.03476
Publisher: https://arxiv.org/abs/1606.03476

Keywords: imitation learning, gail, inverse rl

Abstract ​

We propose a new general framework for directly extracting a policy from data as if it were obtained by reinforcement learning following the expert.

Cite this paper ​

@misc{gail2017,
  title  = {Generative Adversarial Imitation Learning},
  author = {Jonathan Ho, Stefano Ermon},
  year   = {2017},
  journal = {NeurIPS},
  doi    = {10.48550/arXiv.1606.03476},
  url    = {https://doi.org/10.48550/arXiv.1606.03476},
}

Source files ​

• metadata.json
• paper.bib