论文标题
带有局部动力学模型的视觉远见
Visual Foresight With a Local Dynamics Model
论文作者
论文摘要
已证明无模型的政策学习能够学习操纵政策，可以使用单步操作基础来解决长期的视野任务。但是，培训这些政策是一个耗时的过程，需要大量数据。我们提出了局部动力学模型（LDM），该模型有效地学习了这些操纵基原始人的状态转换函数。通过将LDM与无模型的政策学习相结合，我们可以学习可以使用一步lookahead计划来解决复杂的操纵任务的政策。我们表明，LDM既是样本有效的，又超过其他模型架构。与计划结合使用时，我们可以在模拟中的几项具有挑战性的操纵任务上胜过其他基于模型和模型的政策。
Model-free policy learning has been shown to be capable of learning manipulation policies which can solve long-time horizon tasks using single-step manipulation primitives. However, training these policies is a time-consuming process requiring large amounts of data. We propose the Local Dynamics Model (LDM) which efficiently learns the state-transition function for these manipulation primitives. By combining the LDM with model-free policy learning, we can learn policies which can solve complex manipulation tasks using one-step lookahead planning. We show that the LDM is both more sample-efficient and outperforms other model architectures. When combined with planning, we can outperform other model-based and model-free policies on several challenging manipulation tasks in simulation.
