Maneuver decision of UAV in air combat based on deterministic policy gradient.
Junxiao GuoZihan WangJun LanBingchen DongRan LiQiming YangJiandong ZhangPublished in: ICCA (2022)
Keyphrases
- policy gradient
- air combat
- decision making
- parametric optimization
- reinforcement learning
- actor critic
- decision makers
- function approximation
- optimal control
- gradient method
- path planning
- closed loop
- variance reduction
- model free reinforcement learning
- neural network
- reinforcement learning algorithms
- approximation methods
- control algorithm
- state action