TY - GEN
T1 - Game of Marine Robots
T2 - 2023 IEEE International Conference on Development and Learning, ICDL 2023
AU - Wang, Yongkang
AU - Wang, Yong
AU - Cui, Rongxin
AU - Guo, Xinxin
AU - Yan, Weisheng
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this article, an online reinforcement learning (RL) algorithm is studied for the pursuit evasion game of Unmanned Surface Vehicles (USVs), both of which have learning abilities compared to the traditional apparent strategy. The pursuit evasion game between the USVs is described as differential game based on the relative motion equation to overcome the weakness of data-driven learning. The solution to this differential game is obtained by using online RL. The value function, the USV1 (pursuer) strategy, and the USV2 (evader) strategy are approximated by critic, actor 1, and actor 2 neural networks (NNs), respectively. The uniformly ultimately bound (UUB) of the system states and weight errors of NNs are researched based on Lyapunov theory. The performance of the proposed strategy is verified by the simulation results.
AB - In this article, an online reinforcement learning (RL) algorithm is studied for the pursuit evasion game of Unmanned Surface Vehicles (USVs), both of which have learning abilities compared to the traditional apparent strategy. The pursuit evasion game between the USVs is described as differential game based on the relative motion equation to overcome the weakness of data-driven learning. The solution to this differential game is obtained by using online RL. The value function, the USV1 (pursuer) strategy, and the USV2 (evader) strategy are approximated by critic, actor 1, and actor 2 neural networks (NNs), respectively. The uniformly ultimately bound (UUB) of the system states and weight errors of NNs are researched based on Lyapunov theory. The performance of the proposed strategy is verified by the simulation results.
KW - neural networks
KW - pursuit evasion game
KW - reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85182943516&partnerID=8YFLogxK
U2 - 10.1109/ICDL55364.2023.10364460
DO - 10.1109/ICDL55364.2023.10364460
M3 - 会议稿件
AN - SCOPUS:85182943516
T3 - 2023 IEEE International Conference on Development and Learning, ICDL 2023
SP - 121
EP - 126
BT - 2023 IEEE International Conference on Development and Learning, ICDL 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 November 2023 through 11 November 2023
ER -
