2023
DOI: 10.1109/tits.2022.3160757
|View full text |Cite
|
Sign up to set email alerts
|

PPO-Based PDACB Traffic Control Scheme for Massive IoV Communications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 18 publications
(1 citation statement)
references
References 29 publications
0
1
0
Order By: Relevance
“…However, when faced with a high-dimensional or continuous action space, policy-based algorithms are more efficient and easier to reach convergence, and in the face of the state space explosion problem in distributed mobile fog computing, DDPG can be used to solve the optimization problem of the objective in a high-dimensional state space, and also its network mechanism can be combined with Graph Convolutional Networks (GCN), thus achieving improved performance [35,36]. The Proximal Policy Optimization(PPO) algorithm used in this paper, as the most widely applicable algorithm, has an excellent performance in either discrete or continuous state-action spaces, [37] using PPO to solve the optimal objective factor in a reasonable state-action space, obtain accurate continuous actions, and achieve fast convergence.…”
Section: Related Workmentioning
confidence: 99%
“…However, when faced with a high-dimensional or continuous action space, policy-based algorithms are more efficient and easier to reach convergence, and in the face of the state space explosion problem in distributed mobile fog computing, DDPG can be used to solve the optimization problem of the objective in a high-dimensional state space, and also its network mechanism can be combined with Graph Convolutional Networks (GCN), thus achieving improved performance [35,36]. The Proximal Policy Optimization(PPO) algorithm used in this paper, as the most widely applicable algorithm, has an excellent performance in either discrete or continuous state-action spaces, [37] using PPO to solve the optimal objective factor in a reasonable state-action space, obtain accurate continuous actions, and achieve fast convergence.…”
Section: Related Workmentioning
confidence: 99%