Deep reinforcement learning algorithms require large and diverse datasets in order to learn successful policies for perception-based mobile navigation. However, gathering such datasets with a single robot can be prohibitively expensive. Collecting data with multiple different robotic platforms with possibly different dynamics is a more scalable approach to large-scale data collection. But how can deep reinforcement learning algorithms leverage such heterogeneous datasets? In this work, we propose a deep reinforcement learning algorithm with hierarchically integrated models (HInt). At training time, HInt learns separate perception and dynamics models, and at test time, HInt integrates the two models in a hierarchical manner and plans actions with the integrated model. This method of planning with hierarchically integrated models allows the algorithm to train on datasets gathered by a variety of different platforms, while respecting the physical capabilities of the deployment robot at test time. Our mobile navigation experiments show that HInt outperforms conventional hierarchical policies and single-source approaches.
翻译:深度强化学习算法需要大型和多样化的数据集,以便学习基于感知的移动导航的成功政策。 但是, 与单一机器人收集这类数据集可能费用极高。 用多种不同机器人平台收集数据, 可能具有不同动态, 是大规模数据收集的更可伸缩的方法。 但是, 深度强化学习算法如何利用这种多样化的数据集? 在这项工作中, 我们提出一个带有等级整合模型的深度强化学习算法( HINT ) 。 在培训时, HInt 学习不同的感知和动态模型, 在测试时, HInt 以等级化方式将这两个模型整合起来, 并计划与集成模型一起采取行动。 这种以等级整合模型进行规划的方法使得算法能够对不同平台收集的数据集进行培训,同时尊重测试时部署机器人的物理能力。 我们的流动导航实验显示, HInt 超越了常规的等级政策和单一源方法。