论文标题
通过简单的技能模仿学习复杂的技能获取
Complex Skill Acquisition Through Simple Skill Imitation Learning
论文作者
论文摘要
人类经常将复杂的任务视为更简单的子任务的组合，以便更有效地学习这些复杂的任务。例如，反弹可以被认为是四个子技能的组合：跳跃，膝盖，向后滚动和向下推动手臂。在这种推理方面，我们提出了一种新的算法，该算法对简单，易于学习的技能进行神经网络政策进行训练，以培养潜在的空间，以加速模仿复杂，难以学习的技能的模仿学习。我们专注于复杂任务包括更简单子任务的并发（可能是连续的）组合，因此我们的算法可以看作是一种新型的同时层次模仿学习方法。我们在高维环境中评估了有关艰巨任务的算法，发现它在训练速度和整体性能方面始终超过最先进的基线。
Humans often think of complex tasks as combinations of simpler subtasks in order to learn those complex tasks more efficiently. For example, a backflip could be considered a combination of four subskills: jumping, tucking knees, rolling backwards, and thrusting arms downwards. Motivated by this line of reasoning, we propose a new algorithm that trains neural network policies on simple, easy-to-learn skills in order to cultivate latent spaces that accelerate imitation learning of complex, hard-to-learn skills. We focus on the case in which the complex task comprises a concurrent (and possibly sequential) combination of the simpler subtasks, and therefore our algorithm can be seen as a novel approach to concurrent hierarchical imitation learning. We evaluate our algorithm on difficult tasks in a high-dimensional environment and find that it consistently outperforms a state-of-the-art baseline in training speed and overall performance.
