Research on Target Defense Strategy Based on Deep Reinforcement Learning
Open Access
- 30 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 82329-82335
Abstract
Considering the natural advantages of deep reinforcement learning algorithms in dealing with continuous control problems, especially for dynamic interactions, these algorithms can be applied to the Attacker-Defender-Target (ADT) game problems. In this paper, the deep deterministic policy gradient (DDPG) and the multiagent DDPG algorithm are employed to solve the issue of target defense in the ADT game. By introducing an angle between the attacker-target line of sight and the attacker-defender line, we modify the reward function in the deep reinforcement learning algorithm, and redefine the corresponding state space and action space. Through several numerical experiments, the validity of the modified reward function is obvious that the modified defender’s reward function improves the defender’s strategic performance, win rate and interceptive time, in the game. Compared with the traditional differential game theory, the DDPG and multiagent DDPG algorithms with the modified reward function can realize real-time decision-making and improve the flexibility of defenders in the confrontation process.Keywords
This publication has 23 references indexed in Scilit:
- Toward a Solution of the Active Target Defense Differential GameDynamic Games and Applications, 2018
- Two coupled pursuit-evasion games in target-attacker-defender problem2017
- Pursuit Strategy to Capture High-Speed Evaders Using Multiple PursuersJournal of Guidance, Control, and Dynamics, 2017
- Multi-player pursuit–evasion games with one superior evaderAutomatica, 2016
- Cooperative target defense differential game with a constrained-maneuverable Defender2015
- Pursuit-evasion games in the presence of a line segment obstacle2014
- An alliance generation algorithm based on modified particle swarm optimization for multiple emotional robots pursuit-evader problem2014
- Three-Player Pursuit and Evasion ConflictJournal of Guidance, Control, and Dynamics, 2014
- Learning to predict by the methods of temporal differencesMachine Learning, 1988
- Defending a Moving Target Against Missile or Torpedo AttackIEEE Transactions on Aerospace and Electronic Systems, 1976