Some Learning from Demonstrations (LfD) methods handle small mismatches in the action spaces of the teacher and student. Here we address the case where the teacher's morphology is substantially different from that of the student. Our framework, Morphological Adaptation in Imitation Learning (MAIL), bridges this gap allowing us to train an agent from demonstrations by other agents with significantly different morphologies. MAIL learns from suboptimal demonstrations, so long as they provide $\textit{some}$ guidance towards a desired solution. We demonstrate MAIL on manipulation tasks with rigid and deformable objects including 3D cloth manipulation interacting with rigid obstacles. We train a visual control policy for a robot with one end-effector using demonstrations from a simulated agent with two end-effectors. MAIL shows up to $24\%$ improvement in a normalized performance metric over LfD and non-LfD baselines. It is deployed to a real Franka Panda robot, handles multiple variations in properties for objects (size, rotation, translation), and cloth-specific properties (color, thickness, size, material). An overview is on https://uscresl.github.io/mail .

翻译：一些从示教学习（LfD）方法能够处理教师和学生动作空间中的微小不匹配。本文处理教师形态与学生形态显著不同的情况。我们的框架——模仿学习中的形态适应（MAIL），弥合了这一差距，使得我们能够从具有显著不同形态的其他智能体的示教中训练一个智能体。只要示教能对期望解提供$\textit{某些}$指引，MAIL就能从次优示教中学习。我们在涉及刚性和可变形物体的操作任务上展示了MAIL，包括与刚性障碍物交互的三维布料操作。我们利用一个具有两个末端执行器的模拟智能体的示教，训练了一个单末端执行器机器人的视觉控制策略。在归一化性能指标上，MAIL相比LfD和非LfD基线方法显示出高达$24\%$的提升。该方法已部署到真实的Franka Panda机器人上，能够处理物体属性（尺寸、旋转、平移）以及布料特有属性（颜色、厚度、尺寸、材质）的多种变化。概述请见https://uscresl.github.io/mail。