逆动力学学习中的学习状态相关损失
Learning State-Dependent Losses for Inverse Dynamics Learning
摘要：
能够快速适应动态变化是基于模型的控制对象操作任务的最重要的。为了影响逆动力学模型参数的快速自适应，数据效率是至关重要的。给定观察到的数据，优化器如何更新模型参数的一个关键元素是损失函数。在这项工作中，我们建议应用元学习学习结构化的，状态依赖的损失函数在元训练阶段。然后，我们在在线适应任务中用学习到的损失替换标准损失。我们评估我们提出的方法在逆动力学学习任务，无论是在模拟和真实的硬件数据。在这两种设置中，与标准的状态无关的损失函数相比，结构化和状态相关的学习损失提高了在线自适应速度。
英文摘要：
Being able to quickly adapt to changes in dynamics is paramount in model-based control for object manipulation tasks. In order to influence fast adaptation of the inverse dynamics model's parameters, data efficiency is crucial. Given observed data, a key element to how an optimizer updates model parameters is the loss function. In this work, we propose to apply meta-learning to learn structured, state-dependent loss functions during a meta-training phase. We then replace standard losses with our learned losses during online adaptation tasks. We evaluate our proposed approach on inverse dynamics learning tasks, both in simulation and on real hardware data. In both settings, the structured and state-dependent learned losses improve online adaptation speed, when compared to standard, state-independent loss functions.
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。
