Learning Action-Transferable Policy with Action Embedding

Understand

Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning.

• However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage.
• Most previous studies only addressed the inconsistency across different state spaces by learning a common feature space, without considering that similar actions in different action spaces of related tasks share similar semantics.
• In this paper, we propose a method to learning action embeddings by leveraging this idea, and a framework that learns both state embeddings and action embeddings to transfer policy across tasks with different state and action spaces.