Generative Adversarial Imitation Learning from Failed Experiences (Student Abstract)
2020 ◽
Vol 34
(10)
◽
pp. 13997-13998
Keyword(s):
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.
Keyword(s):
2021 ◽
2021 ◽
2015 ◽
Vol 114
(3)
◽
pp. 1577-1592
◽
Keyword(s):
2021 ◽
Vol 70
(1)
◽
pp. 145-151
Keyword(s):