Meta reinforcement learning （Meta-RL） aims at automatically learning induction bias for a new reinforcement learning task from a set of different but related tasks. It plays an important role in improving the sample efficiency and generalization of reinforcement learning algorithm in difficult scenarios. This paper first introduces a framework in which three key components of Meta-RL are identified， i.e.， learning experience （related tasks）， inductive bias and learning objective. Based on this， current research progress in this field is analyzed and reviewed， and the principles and characteristics of several representative algorithms are described. The paper also gives a detailed account of commonly used benchmark environments and performance evaluation methods for meta-RL. The limitation of current research and potential future development directions are also discussed.