Can I read SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models on EtoBox?

SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models by Wan, Shenghua; Wang, Yucen; Shao, Minghao; Chen, Ruying; Zhan, De-Chuan is a scholarly article available to read on EtoBox.

What is SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models about?

Model-based imitation learning (MBIL) is a popular reinforcement learning method that improves sample efficiency on high-dimension input sources, such as images and videos. Following the convention of MBIL research, existing algorithms are highly deceptive by task-irrelevant information, especially moving distractors in videos. To tackle this problem, we propose a new algorithm - named Separated Model-based Adversarial Imitation Learning (SeMAIL) - decoupling the environment dynamics into two parts by task-relevant dependency, which is determined by agent actions, and training separately. In this way, the agent can imagine its trajectories and imitate the expert behavior efficiently in task-relevant state space. Our method achieves near-expert performance on various visual control tasks with complex observations and the more challenging tasks with different backgrounds from expert observations.

Author

Wan, Shenghua; Wang, Yucen; Shao, Minghao; Chen, Ruying; Zhan, De-Chuan

Published

2023

Language

EN