Generative Adversarial Imitation Learning from Failed Experiences (Student Abstract)

Authors

  • Jiacheng Zhu Soochow University
  • Jiahao Lin Soochow University
  • Meng Wang Fuxi AI Lab
  • Yingfeng Chen Fuxi AI Lab
  • Changjie Fan Fuxi AI Lab
  • Chong Jiang Soochow University
  • Zongzhang Zhang Nanjing University

DOI:

https://doi.org/10.1609/aaai.v34i10.7271

Abstract

Imitation learning provides a family of promising methods that learn policies from expert demonstrations directly. As a model-free and on-line imitation learning method, generative adversarial imitation learning (GAIL) generalizes well to unseen situations and can handle complex problems. In this paper, we propose a novel variant of GAIL called GAIL from failed experiences (GAILFE). GAILFE allows an agent to utilize failed experiences in the training process. Moreover, a constrained optimization objective is formalized in GAILFE to balance learning from given demonstrations and from self-generated failed experiences. Empirically, compared with GAIL, GAILFE can improve sample efficiency and learning speed over different tasks.

Downloads

Published

2020-04-03

How to Cite

Zhu, J., Lin, J., Wang, M., Chen, Y., Fan, C., Jiang, C., & Zhang, Z. (2020). Generative Adversarial Imitation Learning from Failed Experiences (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13997-13998. https://doi.org/10.1609/aaai.v34i10.7271

Issue

Section

Student Abstract Track