Complex Skill Acquisition Through Simple Skill Imitation Learning
This addresses the challenge of efficient skill acquisition in robotics or AI, offering a novel approach to hierarchical imitation learning, though it appears incremental as it builds on existing imitation learning methods.
The paper tackles the problem of learning complex tasks by imitating simpler subtasks, proposing an algorithm that trains neural network policies on simple skills to accelerate imitation learning of complex skills, and finds it consistently outperforms a state-of-the-art baseline in training speed and overall performance in high-dimensional environments.
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.