Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control
The real-time railway rescheduling problem is a crucial challenge for human operators since many factors have to be considered during decision making, from the positions and velocities of the vehicles to the different regulations of the individual railway companies. Thanks to that, human operators c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4465 |
| _version_ | 1797505619946635264 |
|---|---|
| author | István Lövétei Bálint Kővári Tamás Bécsi Szilárd Aradi |
| author_facet | István Lövétei Bálint Kővári Tamás Bécsi Szilárd Aradi |
| author_sort | István Lövétei |
| collection | DOAJ |
| description | The real-time railway rescheduling problem is a crucial challenge for human operators since many factors have to be considered during decision making, from the positions and velocities of the vehicles to the different regulations of the individual railway companies. Thanks to that, human operators cannot be expected to provide optimal decisions in a particular situation. Based on the recent successes of multi-agent deep reinforcement learning in challenging control problems, it seems like a suitable choice for such a domain. Consequently, this paper proposes a multi-agent deep reinforcement learning-based approach with different state representational choices to solve the real-time railway rescheduling problem. Furthermore, comparing different methods, the proposed learning-based approaches outperform their competitions, such as the Monte Carlo tree search algorithm, which is utilized as a model-based planner, and also other learning-based methods that utilize different abstractions. The results show that the proposed representation has more significant generalization potential and provides superior performance. |
| first_indexed | 2024-03-10T04:21:13Z |
| format | Article |
| id | doaj.art-b19c78faaa9d407a8b57a3d9d477cacb |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:21:13Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b19c78faaa9d407a8b57a3d9d477cacb2023-11-23T07:49:23ZengMDPI AGApplied Sciences2076-34172022-04-01129446510.3390/app12094465Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic ControlIstván Lövétei0Bálint Kővári1Tamás Bécsi2Szilárd Aradi3Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, H-1111 Budapest, HungaryDepartment of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, H-1111 Budapest, HungaryDepartment of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, H-1111 Budapest, HungaryDepartment of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, H-1111 Budapest, HungaryThe real-time railway rescheduling problem is a crucial challenge for human operators since many factors have to be considered during decision making, from the positions and velocities of the vehicles to the different regulations of the individual railway companies. Thanks to that, human operators cannot be expected to provide optimal decisions in a particular situation. Based on the recent successes of multi-agent deep reinforcement learning in challenging control problems, it seems like a suitable choice for such a domain. Consequently, this paper proposes a multi-agent deep reinforcement learning-based approach with different state representational choices to solve the real-time railway rescheduling problem. Furthermore, comparing different methods, the proposed learning-based approaches outperform their competitions, such as the Monte Carlo tree search algorithm, which is utilized as a model-based planner, and also other learning-based methods that utilize different abstractions. The results show that the proposed representation has more significant generalization potential and provides superior performance.https://www.mdpi.com/2076-3417/12/9/4465multi-agent deep reinforcement learningreal-time railway reschedulingMonte Carlo tree search |
| spellingShingle | István Lövétei Bálint Kővári Tamás Bécsi Szilárd Aradi Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control Applied Sciences multi-agent deep reinforcement learning real-time railway rescheduling Monte Carlo tree search |
| title | Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control |
| title_full | Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control |
| title_fullStr | Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control |
| title_full_unstemmed | Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control |
| title_short | Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control |
| title_sort | environment representations of railway infrastructure for reinforcement learning based traffic control |
| topic | multi-agent deep reinforcement learning real-time railway rescheduling Monte Carlo tree search |
| url | https://www.mdpi.com/2076-3417/12/9/4465 |
| work_keys_str_mv | AT istvanlovetei environmentrepresentationsofrailwayinfrastructureforreinforcementlearningbasedtrafficcontrol AT balintkovari environmentrepresentationsofrailwayinfrastructureforreinforcementlearningbasedtrafficcontrol AT tamasbecsi environmentrepresentationsofrailwayinfrastructureforreinforcementlearningbasedtrafficcontrol AT szilardaradi environmentrepresentationsofrailwayinfrastructureforreinforcementlearningbasedtrafficcontrol |