导航

ACTA AERONAUTICAET ASTRONAUTICA SINICA ›› 2020, Vol. 41 ›› Issue (S2): 724285-724285.doi: 10.7527/S1000-6893.2020.24285

Previous Articles     Next Articles

Learning method for autonomous air combat based on experience transfer

ZHOU Kai1,2, WEI Ruixuan2, ZHANG Qirui3, DING Chao1,2   

  1. 1. Graduate College, Air Force Engineering University, Xi'an 710051, China;
    2. Aeronautics Engineering College, Air Force Engineering University, Xi'an 710038, China;
    3. Unit 95561 of PLA, Rikaze City 857000, China
  • Received:2020-05-15 Revised:2020-05-30 Published:2020-06-18
  • Supported by:
    Science and Technology Innovation 2030-Key Project of "New Generation Artificial Intelligence" (2018AAA0102403); National Natural Science Foundation of China (61573373)

Abstract: Most of the existing machine learning methods are in interactive learning mode, whose training process relies heavily on the interactive data with the environment. Air combat is a training mission with sparse rewards, with the system usually exploring for a long period of time to find actions that can obtain rewards during the beginning stage of learning. Retraining for every new mission wastes the computing resources. Therefore, a learning method based on experience transfer is designed in this paper, enabling the trained agent to share knowledge with the new agent and thereby improving its learning efficiency in the new task. First of all, a learning model based on experience transfer is constructed by referring to the phenomenon that mankind can learn rapidly through experiences. Secondly, considering both the knowledge sharing and characteristics of the new task, the connotation of experience is defined, and a cognitive mode of "knowledge + task → experience" is established. Thirdly, a reference learning method is designed, combining external experience with the task to further transform it into knowledge of the new agent. Finally, using experience applicability as the screening index, we analyze the influence of experience applicability on the reference learning efficiency, determining the screening boundary of implementing the reference learning. The new agent can therefore obtain preliminary knowledge about the new mission by reference learning and find action policies that can obtain reward so as to improve the learning speed in the new learning mission.

Key words: air combat, experience transfer, reference learning, knowledge sharing, fusion cognition

CLC Number: