Table 6.

Placement and trajectory issues in ML-enhanced UAV networks.

Reference	Placement and Trajectory Target	ML Solution
Liu  et al. [109]	Throughput	Q-learning
Ladosz  et al. [110]	Throughput	GP and NMPC based
Bayerlein et al. [111]	Sum-rate	Q-learning
Ladosz  et al. [112]	Communication quality	NN
Liu et al. [113]	MOS and QoE	Q-learning
Peng et al. [115]	Mobility prediction and object profiling	Unsupervised learning
Esrafilian et al. [116]	Throughput and path planning	Map compression based
Colonnese et al. [118]	QoE	Q-learning
Dai  et al. [119]	Sum-rate	Distributed learning
Jailton  et al. [120]	Throughput	ANN
Klaine  et al. [121]	Radio coverage	Q-learning
Ghanavi  et al. [122]	QoS	Q-learning
Mozaffari  et al. [101]	Latency	Kernel density estimation
Wu  et al. [123]	Spectral efficiency	DQN
Hu  et al. [124]	Coordination of multiple UAVs	Q-learning
Liu  et al. [126]	Radio coverage	Decentralized DRL
Liu  et al. [128]	QoS	Double Q-learning
Huang et al. [129]	Radio Coverage	DRL
Lu  et al. [130]	Energy efficiency	SMGD