Third-Person Imitation Learning via Image Difference and Variational Discriminator Bottleneck (Student Abstract)

Chong Jiang, Zongzhang Zhang, Zixuan Chen, Jiacheng Zhu, Junpeng Jiang

AAAI 2020 pp. 13819-13820

doi:10.1609/AAAI.V34I10.7181 /aaai/2020/jiang2020aaai-third/

Abstract

Third-person imitation learning (TPIL) is a variant of generative adversarial imitation learning and can learn an expert-like policy from third-person expert demonstrations. Third-person expert demonstrations usually exist in the form of videos recorded in a third-person perspective, and there is a lack of direct correspondence with samples generated by agent. To alleviate this problem, we improve TPIL by applying image difference and variational discriminator bottleneck. Empirically, our new method has better performance than TPIL on two MuJoCo tasks, Reacher and Inverted Pendulum.

PDF AAAI Semantic Scholar

Cite

Text

Jiang et al. "Third-Person Imitation Learning via Image Difference and Variational Discriminator Bottleneck (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7181

Markdown

[Jiang et al. "Third-Person Imitation Learning via Image Difference and Variational Discriminator Bottleneck (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/jiang2020aaai-third/) doi:10.1609/AAAI.V34I10.7181

BibTeX

@inproceedings{jiang2020aaai-third,
  title     = {{Third-Person Imitation Learning via Image Difference and Variational Discriminator Bottleneck (Student Abstract)}},
  author    = {Jiang, Chong and Zhang, Zongzhang and Chen, Zixuan and Zhu, Jiacheng and Jiang, Junpeng},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13819-13820},
  doi       = {10.1609/AAAI.V34I10.7181},
  url       = {https://mlanthology.org/aaai/2020/jiang2020aaai-third/}
}