Domain Adaptation for Imitation Learning Using Generative Adversarial Network

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 14; p. 4718
• Main Authors: Nguyen Duc, Tho, Tran, Chanh Minh, Tan, Phan Xuan, Kamioka, Eiji
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 09-07-2021; MDPI
• Subjects: Adaptation; Behavior; domain adaptive imitation learning; generative adversarial network; imitation learning; Learning; Performance evaluation; Task complexity
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21144718

Imitation learning is an effective approach for an autonomous agent to learn control policies when an explicit reward function is unavailable, using demonstrations provided from an expert. However, standard imitation learning methods assume that the agents and the demonstrations provided by the expert are in the same domain configuration. Such an assumption has made the learned policies difficult to apply in another distinct domain. The problem is formalized as domain adaptive imitation learning, which is the process of learning how to perform a task optimally in a learner domain, given demonstrations of the task in a distinct expert domain. We address the problem by proposing a model based on Generative Adversarial Network. The model aims to learn both domain-shared and domain-specific features and utilizes it to find an optimal policy across domains. The experimental results show the effectiveness of our model in a number of tasks ranging from low to complex high-dimensional.