CCIL：用于纠正性模仿学习的基于连续性的数据增强
CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning
AI总结：
提出CCIL技术，利用环境动力学的局部连续性生成纠正性标签以增强模仿学习对复合误差和扰动的鲁棒性，在多种机器人仿真领域验证了有效性。
摘要：
我们提出了一种新技术，通过生成纠正性数据来应对复合误差和干扰，从而增强模仿学习方法的鲁棒性。现有方法依赖交互式专家标注、额外的离线数据集或特定领域的不变性，而我们的方法除了需要访问专家数据外，几乎不需要额外的假设。关键见解是利用环境动力学中的局部连续性来生成纠正性标签。该方法首先从专家演示中构建动力学模型，并促使学习到的模型保持局部Lipschitz连续性。在局部连续的区域中，该模型使我们能够在演示的邻域内、但超出数据集中实际状态和动作集合的范围之外生成纠正性标签。在这种增强数据上进行训练，提升了智能体从扰动中恢复并处理复合误差的能力。我们通过在仿真环境中的多种机器人领域进行实验，验证了所生成标签的有效性，这些领域具有不同形式的连续性和不连续性，包括经典控制问题、无人机飞行、具有高维传感器观测的导航、有腿运动以及桌面操作。
英文摘要：
We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing methods rely on interactive expert labeling, additional offline datasets, or domain-specific invariances, our approach requires minimal additional assumptions beyond access to expert data. The key insight is to leverage local continuity in the environment dynamics to generate corrective labels. Our method first constructs a dynamics model from the expert demonstration, encouraging local Lipschitz continuity in the learned model. In locally continuous regions, this model allows us to generate corrective labels within the neighborhood of the demonstrations but beyond the actual set of states and actions in the dataset. Training on this augmented data enhances the agent's ability to recover from perturbations and deal with compounding errors. We demonstrate the effectiveness of our generated labels through experiments in a variety of robotics domains in simulation that have distinct forms of continuity and discontinuity, including classic control problems, drone flying, navigation with high-dimensional sensor observations, legged locomotion, and tabletop manipulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
