Uneingeschränkter Zugang

UAV Path Planning Based on Deep Reinforcement Learning

 und   
15. März 2024

Zitieren
COVER HERUNTERLADEN

Figure 1.

Reinforcement learning model
Reinforcement learning model

Figure 2.

Basic model of deep reinforcement learning
Basic model of deep reinforcement learning

Figure 3.

DQN algorithm structure diagram
DQN algorithm structure diagram

Figure 4.

DQN algorithm learning results
DQN algorithm learning results

Figure 5.

DQN algorithm learning results
DQN algorithm learning results

dqn simulation parameters

Parameters Value
Size of the replay memory pool D 5000
Size of Mini-batch 64
Discount Factor γ 0.9
Initial exploration rate ε 0.9
Learning Rate 0.0002
Neural network activation function ReLU
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
4 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Informatik, Informatik, andere