Deep Reinforcement Learning: A Survey

Deep reinforcement learning (DRL) integrates the feature representation ability of deep learning with the decision-making ability of reinforcement learning so that it can achieve powerful end-to-end learning control capabilities. In the past decade, DRL has made substantial advances in many tasks that require perceiving high-dimensional input and making optimal or near-optimal decisions. However, there are still many challenging problems in the theory and applications of DRL, especially in learning control tasks with limited samples, sparse rewards, and multiple agents. Researchers have proposed various solutions and new theories to solve these problems and promote the development of DRL. In addition, deep…

• NN
  National Natural Science Foundation of China

  Awards: 61772396, 61772392, 61825305, 61902296
• CP
  China Postdoctoral Science Foundation

  Award: 2019M663640
• NS
  Natural Science Foundation of Shaanxi Province

  Awards: 2020JQ-330, 2020JM-195
• NK
  National Key Research and Development Program of China

  Award: 2018YFC0807500