English

Complex Skill Acquisition Through Simple Skill Imitation Learning

Machine Learning 2020-10-21 v4 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2007.10281,
  title  = {Complex Skill Acquisition Through Simple Skill Imitation Learning},
  author = {Pranay Pasula},
  journal= {arXiv preprint arXiv:2007.10281},
  year   = {2020}
}

Comments

7 pages, 2 figures; Fixed typos