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

中文翻译：

---

对抗性行为克隆

摘要 模仿学习已广泛应用于自主机器人控制。一种流行的 IL 方法是学徒学习 (AL)，它交替使用 RL 和逆强化学习 (IRL)。AL从根本上需要大量的环境交互，因此需要很长时间的训练。我们相信，如果交互次数可以减少到尽可能接近于零，IL 算法将更适用于现实世界的问题。在本文中，我们提出了一种称为对抗性行为克隆 (ABC) 的 IL 算法。MuJoCo 物理模拟器上的实验结果表明，即使没有任何环境交互，我们的算法也能通过最先进的 AL 算法即生成对抗性模仿学习 (GAIL) 取得有竞争力的结果。图形概要