利用前向模型预测误差的学习控制
Leveraging Forward Model Prediction Error for Learning Control
摘要：
基于模型的控制的学习可以是样本有效的，并且可以很好地推广，但是成功地学习代表手头问题的模型和控制器对于复杂任务来说可能是具有挑战性的。使用不准确的模型进行学习可能会导致次优解决方案，这在实践中不太可能表现良好。在这项工作中，我们提出了一种学习方法，它在模型学习和数据汇集之间迭代，并利用前向模型预测误差进行学习控制。我们展示了如何使用控制器的预测作为输入到一个正向模型可以创建一个可微的控制器和模型之间的连接，使我们能够制定在状态空间中的损失。这让我们在控制器学习过程中包括前向模型预测误差，我们表明这会创建一个损失目标，从而显着改善对不同电机控制任务的学习。我们提供的经验和理论结果表明，我们的方法的好处，并在模拟学习控制7自由度机械手和欠驱动12自由度四足动物目前的评估。我们表明，我们的方法成功地学习控制器具有挑战性的电机控制任务，涉及接触开关。
英文摘要：
Learning for model based control can be sample-efficient and generalize well, however successfully learning models and controllers that represent the problem at hand can be challenging for complex tasks. Using inaccurate models for learning can lead to sub-optimal solutions, that are unlikely to perform well in practice. In this work, we present a learning approach which iterates between model learning and data collection and leverages forward model prediction error for learning control. We show how using the controller's prediction as input to a forward model can create a differentiable connection between the controller and the model, allowing us to formulate a loss in the state space. This lets us include forward model prediction error during controller learning and we show that this creates a loss objective that significantly improves learning on different motor control tasks. We provide empirical and theoretical results that show the benefits of our method and present evaluations in simulation for learning control on a 7 DoF manipulator and an underactuated 12 DoF quadruped. We show that our approach successfully learns controllers for challenging motor control tasks involving contact switching.
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。
