SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision
With the advancement of autonomous driving technology, vehicle lane-change decision (LCD) has become a critical issue for improving driving safety and efficiency. Traditional deep reinforcement learning (DRL) methods face challenges such as slow convergence, unstable decisions, and low accuracy when...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/2/235 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588043479941120 |
|---|---|
| author | Yang Liu Tianxing Yang Liwei Tian Jianbiao Pei |
| author_facet | Yang Liu Tianxing Yang Liwei Tian Jianbiao Pei |
| author_sort | Yang Liu |
| collection | DOAJ |
| description | With the advancement of autonomous driving technology, vehicle lane-change decision (LCD) has become a critical issue for improving driving safety and efficiency. Traditional deep reinforcement learning (DRL) methods face challenges such as slow convergence, unstable decisions, and low accuracy when dealing with complex traffic environments. To address these issues, this paper proposes a novel integrated deep reinforcement learning model called “SGD-TripleQNet” for autonomous vehicle lane-change decision-making. This method integrates three types of deep Q-learning networks (DQN, DDQN, and Dueling DDQN) and uses the Stochastic Gradient Descent (SGD) optimization algorithm to dynamically adjust the network weights. This dynamic weight adjustment process fine-tunes the weights based on gradient information to minimize the target loss function. The approach effectively addresses key challenges in autonomous driving lane-change decisions, including slow convergence, low accuracy, and unstable decision-making. The experiment shows that the proposed method, SGD-TripleQNet, has significant advantages over single models: In terms of convergence speed, it is approximately 25% faster than DQN, DDQN, and Dueling DDQN, achieving stability within 150 epochs; in terms of decision stability, the Q-value fluctuations are reduced by about 40% in the later stages of training; in terms of final performance, the average reward exceeds that of DQN (by 6.85%), DDQN (by 6.86%), and Dueling DDQN (by 6.57%), confirming the effectiveness of the proposed method. It also provides a theoretical foundation and practical guidance for the design and optimization of future autonomous driving systems. |
| format | Article |
| id | doaj-art-1ccb32a34e1149208b9198de234b8c5f |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-1ccb32a34e1149208b9198de234b8c5f2025-01-24T13:39:50ZengMDPI AGMathematics2227-73902025-01-0113223510.3390/math13020235SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change DecisionYang Liu0Tianxing Yang1Liwei Tian2Jianbiao Pei3College of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, ChinaCollege of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, ChinaCollege of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, ChinaCollege of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, ChinaWith the advancement of autonomous driving technology, vehicle lane-change decision (LCD) has become a critical issue for improving driving safety and efficiency. Traditional deep reinforcement learning (DRL) methods face challenges such as slow convergence, unstable decisions, and low accuracy when dealing with complex traffic environments. To address these issues, this paper proposes a novel integrated deep reinforcement learning model called “SGD-TripleQNet” for autonomous vehicle lane-change decision-making. This method integrates three types of deep Q-learning networks (DQN, DDQN, and Dueling DDQN) and uses the Stochastic Gradient Descent (SGD) optimization algorithm to dynamically adjust the network weights. This dynamic weight adjustment process fine-tunes the weights based on gradient information to minimize the target loss function. The approach effectively addresses key challenges in autonomous driving lane-change decisions, including slow convergence, low accuracy, and unstable decision-making. The experiment shows that the proposed method, SGD-TripleQNet, has significant advantages over single models: In terms of convergence speed, it is approximately 25% faster than DQN, DDQN, and Dueling DDQN, achieving stability within 150 epochs; in terms of decision stability, the Q-value fluctuations are reduced by about 40% in the later stages of training; in terms of final performance, the average reward exceeds that of DQN (by 6.85%), DDQN (by 6.86%), and Dueling DDQN (by 6.57%), confirming the effectiveness of the proposed method. It also provides a theoretical foundation and practical guidance for the design and optimization of future autonomous driving systems.https://www.mdpi.com/2227-7390/13/2/235autonomous drivingdeep reinforcement learninglane-change decisionstochastic gradient descent (SGD) optimization algorithm |
| spellingShingle | Yang Liu Tianxing Yang Liwei Tian Jianbiao Pei SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision Mathematics autonomous driving deep reinforcement learning lane-change decision stochastic gradient descent (SGD) optimization algorithm |
| title | SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision |
| title_full | SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision |
| title_fullStr | SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision |
| title_full_unstemmed | SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision |
| title_short | SGD-TripleQNet: An Integrated Deep Reinforcement Learning Model for Vehicle Lane-Change Decision |
| title_sort | sgd tripleqnet an integrated deep reinforcement learning model for vehicle lane change decision |
| topic | autonomous driving deep reinforcement learning lane-change decision stochastic gradient descent (SGD) optimization algorithm |
| url | https://www.mdpi.com/2227-7390/13/2/235 |
| work_keys_str_mv | AT yangliu sgdtripleqnetanintegrateddeepreinforcementlearningmodelforvehiclelanechangedecision AT tianxingyang sgdtripleqnetanintegrateddeepreinforcementlearningmodelforvehiclelanechangedecision AT liweitian sgdtripleqnetanintegrateddeepreinforcementlearningmodelforvehiclelanechangedecision AT jianbiaopei sgdtripleqnetanintegrateddeepreinforcementlearningmodelforvehiclelanechangedecision |