In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of foremost interest. In this work, we analyze this trade-off for low-level policy pre-training with a new benchmark suite of diverse, sparse-reward tasks for bipedal robots. We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner. For utilization on downstream tasks, we present a three-layered hierarchical learning algorithm to automatically trade off between general and specific skills as required by the respective task. In our experiments, we show that our approach performs this trade-off effectively and achieves better results than current state-of-the-art methods for end- to-end hierarchical reinforcement learning and unsupervised skill discovery. Code and videos are available at https://facebookresearch.github.io/hsd3 .
翻译:在强化学习中,经过预先训练的低水平技能有可能极大地促进探索,然而,需要事先了解下游任务,才能在技能设计的一般性(精密控制)和特殊性(更迅速地学习)之间取得适当的平衡。在以往关于连续控制的工作中,尚未明确处理各种方法对这项权衡的敏感性,因为locomotion为航行任务提供了适当的前程,而导航任务一直是最感兴趣的。在这项工作中,我们分析了低层次政策培训前的权衡,为双级机器人提供了一套新的基准,其中包括多样化、稀薄的升级任务。我们提出一个等级技能学习框架,以不受监督的方式获得不同复杂技能,从而减轻了对先前知识的需要。关于下游任务的利用,我们提出了一个三层等级学习算法,以自动交换各项任务所要求的一般技能与具体技能。在我们的实验中,我们展示了我们的方法是有效地进行这种交换,并取得了比目前最先进的最后至更高级强化等级学习和未受监视的技能发现更好的成果。http/Cocudeal and videoblios。