2021
DOI: 10.3390/jmse9111267
|View full text |Cite
|
Sign up to set email alerts
|

An Improved Dueling Deep Double-Q Network Based on Prioritized Experience Replay for Path Planning of Unmanned Surface Vehicles

Abstract: Unmanned Surface Vehicle (USV) has a broad application prospect and autonomous path planning as its crucial technology has developed into a hot research direction in the field of USV research. This paper proposes an Improved Dueling Deep Double-Q Network Based on Prioritized Experience Replay (IPD3QN) to address the slow and unstable convergence of traditional Deep Q Network (DQN) algorithms in autonomous path planning of USV. Firstly, we use the deep double Q-Network to decouple the selection and calculation … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 19 publications
(11 citation statements)
references
References 17 publications
0
6
0
Order By: Relevance
“…The PER-DDQN improves the learning effect and the learning speed by introducing the DDQN and priority experience replay. Two Q -networks are used in DDQN to eliminate the bias caused by the greedy policy [ 34 ]. The current Q -network is used to calculate the action corresponding to the maximum Q -value, and the target Q -network is used to calculate the target Q -value corresponding to the maximum action.…”
Section: Methodsmentioning
confidence: 99%
“…The PER-DDQN improves the learning effect and the learning speed by introducing the DDQN and priority experience replay. Two Q -networks are used in DDQN to eliminate the bias caused by the greedy policy [ 34 ]. The current Q -network is used to calculate the action corresponding to the maximum Q -value, and the target Q -network is used to calculate the target Q -value corresponding to the maximum action.…”
Section: Methodsmentioning
confidence: 99%
“…Though dueling DQN can show better performance than DQN, it is known to take vastly more training time and require larger networks as compared to DQN. 43 Similarly, several enhancements to experience replay techniques, such as prioritized experience replay 44 and hindsight experience replay, 45 could improve performance but take a longer training time as compared to DQN.…”
Section: Future Workmentioning
confidence: 99%
“…Unmanned Surface Vehicle (USV) has a broad application prospect and autonomous path planning as its crucial technology has developed into a hot research direction in the field of USV research [3,4]. Paper [5] proposes an Improved Dueling Deep Double-Q Network Based on Prioritized Experience Replay (IPD3QN) to address the slow and unstable convergence of traditional Deep Q Network (DQN) algorithms in the autonomous path planning of USV. Firstly, the authors used the deep double Q-Network to decouple the selection and calculation of the target Q value action to eliminate overestimation.…”
Section: Artificial Intelligence In Marine Science and Engineeringmentioning
confidence: 99%