Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning
Vehicle simulation algorithms play a crucial role in enhancing traffic efficiency and safety by predicting and evaluating vehicle behavior in various traffic scenarios. Recently, vehicle simulation algorithms based on reinforcement learning have demonstrated excellent performance in practical tasks...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/24/5029 |
| _version_ | 1797381324141494272 |
|---|---|
| author | Yunzhuo Liu Ruoning Zhang Shijie Zhou |
| author_facet | Yunzhuo Liu Ruoning Zhang Shijie Zhou |
| author_sort | Yunzhuo Liu |
| collection | DOAJ |
| description | Vehicle simulation algorithms play a crucial role in enhancing traffic efficiency and safety by predicting and evaluating vehicle behavior in various traffic scenarios. Recently, vehicle simulation algorithms based on reinforcement learning have demonstrated excellent performance in practical tasks due to their ability to exhibit superior performance with zero-shot learning. However, these algorithms face challenges in field adaptation problems when deployed in task sets with variable-dimensional observations, primarily due to the inherent limitations of neural network models. In this paper, we propose a neural network structure accommodating variations in specific dimensions to enhance existing reinforcement learning methods. Building upon this, a scene-compatible vehicle simulation algorithm is designed. We conducted experiments on multiple tasks and scenarios using the Highway-Env traffic environment simulator. The results of our experiments demonstrate that the algorithm can successfully operate on all tasks using a neural network model with fixed shape, even with variable-dimensional observations. Our model exhibits no degradation in simulation performance when compared to the baseline algorithm. |
| first_indexed | 2024-03-08T20:49:47Z |
| format | Article |
| id | doaj.art-6c388623c0f24cc597eabdd627eb9f43 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T20:49:47Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6c388623c0f24cc597eabdd627eb9f432023-12-22T14:05:17ZengMDPI AGElectronics2079-92922023-12-011224502910.3390/electronics12245029Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement LearningYunzhuo Liu0Ruoning Zhang1Shijie Zhou2School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaVehicle simulation algorithms play a crucial role in enhancing traffic efficiency and safety by predicting and evaluating vehicle behavior in various traffic scenarios. Recently, vehicle simulation algorithms based on reinforcement learning have demonstrated excellent performance in practical tasks due to their ability to exhibit superior performance with zero-shot learning. However, these algorithms face challenges in field adaptation problems when deployed in task sets with variable-dimensional observations, primarily due to the inherent limitations of neural network models. In this paper, we propose a neural network structure accommodating variations in specific dimensions to enhance existing reinforcement learning methods. Building upon this, a scene-compatible vehicle simulation algorithm is designed. We conducted experiments on multiple tasks and scenarios using the Highway-Env traffic environment simulator. The results of our experiments demonstrate that the algorithm can successfully operate on all tasks using a neural network model with fixed shape, even with variable-dimensional observations. Our model exhibits no degradation in simulation performance when compared to the baseline algorithm.https://www.mdpi.com/2079-9292/12/24/5029vehicle simulationdeep neural networkreinforcement learningfield adaptationvariable-dimensional observations |
| spellingShingle | Yunzhuo Liu Ruoning Zhang Shijie Zhou Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning Electronics vehicle simulation deep neural network reinforcement learning field adaptation variable-dimensional observations |
| title | Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning |
| title_full | Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning |
| title_fullStr | Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning |
| title_full_unstemmed | Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning |
| title_short | Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning |
| title_sort | vehicle simulation algorithm for observations with variable dimensions based on deep reinforcement learning |
| topic | vehicle simulation deep neural network reinforcement learning field adaptation variable-dimensional observations |
| url | https://www.mdpi.com/2079-9292/12/24/5029 |
| work_keys_str_mv | AT yunzhuoliu vehiclesimulationalgorithmforobservationswithvariabledimensionsbasedondeepreinforcementlearning AT ruoningzhang vehiclesimulationalgorithmforobservationswithvariabledimensionsbasedondeepreinforcementlearning AT shijiezhou vehiclesimulationalgorithmforobservationswithvariabledimensionsbasedondeepreinforcementlearning |