Generative Adversarial Imitation Learning from Failed Experiences (Student 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.

Authors

• Jiacheng Zhu
• Jiahao Lin
• Meng Wang
• Yingfeng Chen
• Changjie Fan Fuxi AI Lab, NetEase, Inc.
• Chong Jiang
• Zongzhang Zhang National Key Laboratory for Novel Software Technology, Nanjing University, China School of Artificial Intelligence, Nanjing University, China

Keywords

No keywords are indexed for this paper.