Accurately predicting the dynamics of robotic systems is crucial for model-based control and reinforcement learning. The most common way to estimate dynamics is by fitting a one-step ahead prediction model and using it to recursively propagate the predicted state distribution over long horizons. Unfortunately, this approach is known to compound even small prediction errors, making long-term predictions inaccurate. In this paper, we propose a new parametrization to supervised learning on state-action data to stably predict at longer horizons -- that we call a trajectory-based model. This trajectory-based model takes an initial state, a future time index, and control parameters as inputs, and directly predicts the state at the future time index. Experimental results in simulated and real-world robotic tasks show that trajectory-based models yield significantly more accurate long term predictions, improved sample efficiency, and the ability to predict task reward. With these improved prediction properties, we conclude with a demonstration of methods for using the trajectory-based model for control.
翻译:精确预测机器人系统的动态对于基于模型的控制和强化学习至关重要。 估计动态的最常用方法是先安装一个预先一步的预测模型,然后用它来反复传播长期的预测状态分布。 不幸的是,这一方法已知甚至会增加一些小的预测错误,使长期预测不准确。 在本文中,我们提议一种新的平衡,以监督国家行动数据方面的学习,从而在更远的视野上进行预测,我们称之为基于轨迹的模型。这个基于轨迹的模式首先采用状态,未来的时间指数和控制参数作为投入,并直接预测未来时间指数的状况。 模拟和现实世界机器人任务的实验结果显示,基于轨迹的模型产生更准确的长期预测,提高样本效率,以及预测任务奖励的能力。有了这些改进的预测特性,我们最后以使用基于轨迹的模型进行控制的方法为例。