| Summary: | In recent years, deep reinforcement learning methods have achieved impressive performance in many different fields, including playing games, robotics, and dialogue systems. However, there are still a lot of restrictions here, one of which is the demand for massive amounts of sampled data. In this paper, a hierarchical meta-learning method based on the actor-critic algorithm is proposed for sample efficient learning. This method provides the transferable knowledge that can efficiently train an actor on a new task with a few trials. Specifically, a global basic critic, meta critic, and task specified network are shared within a distribution of tasks and are capable of criticizing any actor trying to solve any specified task. The hierarchical framework is applied to a critic network in the actor-critic algorithm for distilling meta-knowledge above the task level and addressing distinct tasks. The proposed method is evaluated on multiple classic control tasks with reinforcement learning algorithms, including the start-of-the-art meta-learning methods. The experimental results statistically demonstrate that the proposed method achieves state-of-the-art performance and attains better results with more depth of meta critic network.
|
|---|