A deep reinforcement learning based distributed multi-UAV dynamic area coverage algorithm for complex environment.
Jian XiaoGuohui YuanYuxi XueJinhui HeYaoting WangYuanjiang ZouZhuoran WangPublished in: Neurocomputing (2024)
Keyphrases
- dynamic programming
- reinforcement learning
- learning algorithm
- detection algorithm
- complex environments
- optimization algorithm
- computational complexity
- worst case
- multi agent
- path planning
- matching algorithm
- k means
- computational cost
- dynamic environments
- np hard
- cost function
- significant improvement
- optimal solution
- objective function
- neural network
- expectation maximization
- monte carlo
- cooperative
- evaluation function
- recognition algorithm
- model free