Adversarial behavioral cloning. (2nd May 2020)

• Record Type: Journal Article
• Authors: Sasaki, Fumihiro; Yohira, Tetsuya; Kawaguchi, Atsuo
• Is Part Of: Advanced robotics. Volume 34:Number 9(2020)
• Page Start: 592
• Page End: 598
• Publication Date: 2020-05-02
• Subjects: Imitation learning -- behavioral cloning -- reinforcement learning -- inverse reinforcement learning -- generative adversarial networks; Robotics -- Periodicals; Robotics -- Japan -- Periodicals; Robotics; Japan; Periodicals; 629.89205
• DOI: 10.1080/01691864.2020.1729237
• Languages: English
• ISSNs: 0169-1864

Abstract

ABSTRACT: Imitation learning has been widely applied for autonomous robotics control. A popular IL approach is apprenticeship learning (AL) which alternates RL and inverse reinforcement learning (IRL). AL fundamentally requires a large number of environment interactions and thus takes a long time for training. We believe that IL algorithms would be more applicable to real-world problems if the number of interactions could be reduced as close to zero as possible. In this paper, we propose an IL algorithm which we call Adversarial Behavioral Cloning (ABC) . Experimental results on MuJoCo physics simulator show that our algorithm achieves competitive results with a state-of-the-art AL algorithm, namely generative adversarial imitation learning (GAIL), even without any environment interactions. GRAPHICAL ABSTRACT: