Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-19978| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | Improving sample efficiency and multi-agent communication in RL-based train rescheduling |
| Authors: | Roost, Dano Meier, Ralph Huschauer, Stephan Nygren, Erik Egli, Adrian Weiler, Andreas Stadelmann, Thilo |
| et. al: | No |
| DOI: | 10.21256/zhaw-19978 |
| Proceedings: | Proceedings of the 7th SDS |
| Conference details: | 7th Swiss Conference on Data Science, Lucerne, Switzerland, 26 June 2020 |
| Issue Date: | 26-Jun-2020 |
| Publisher / Ed. Institution: | IEEE |
| Language: | English |
| Subjects: | Multi-agent deep reinforcement learning |
| Subject (DDC): | 006: Special computer methods |
| Abstract: | We present preliminary results from our sixth placed entry to the Flatland international competition for train rescheduling, including two improvements for optimized reinforcement learning (RL) training efficiency, and two hypotheses with respect to the prospect of deep RL for complex real-world control tasks: first, that current state of the art policy gradient methods seem inappropriate in the domain of high-consequence environments; second, that learning explicit communication actions (an emerging machine-to-machine language, so to speak) might offer a remedy. These hypotheses need to be confirmed by future work. If confirmed, they hold promises with respect to optimizing highly efficient logistics ecosystems like the Swiss Federal Railways railway network. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/19978 |
| Fulltext version: | Accepted version |
| License (according to publishing contract): | Licence according to publishing contract |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Computer Science (InIT) |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2020_Roost-etal_RL-based-train-rescheduling_SDS2020.pdf | Accepted Version | 347.87 kB | Adobe PDF |  View/Open |
Show full item record
Roost, D., Meier, R., Huschauer, S., Nygren, E., Egli, A., Weiler, A., & Stadelmann, T. (2020, June 26). Improving sample efficiency and multi-agent communication in RL-based train rescheduling. Proceedings of the 7th SDS. https://doi.org/10.21256/zhaw-19978
Roost, D. et al. (2020) ‘Improving sample efficiency and multi-agent communication in RL-based train rescheduling’, in Proceedings of the 7th SDS. IEEE. Available at: https://doi.org/10.21256/zhaw-19978.
D. Roost et al., “Improving sample efficiency and multi-agent communication in RL-based train rescheduling,” in Proceedings of the 7th SDS, Jun. 2020. doi: 10.21256/zhaw-19978.
ROOST, Dano, Ralph MEIER, Stephan HUSCHAUER, Erik NYGREN, Adrian EGLI, Andreas WEILER und Thilo STADELMANN, 2020. Improving sample efficiency and multi-agent communication in RL-based train rescheduling. In: Proceedings of the 7th SDS. Conference paper. IEEE. 26 Juni 2020
Roost, Dano, Ralph Meier, Stephan Huschauer, Erik Nygren, Adrian Egli, Andreas Weiler, and Thilo Stadelmann. 2020. “Improving Sample Efficiency and Multi-Agent Communication in RL-Based Train Rescheduling.” Conference paper. In Proceedings of the 7th SDS. IEEE. https://doi.org/10.21256/zhaw-19978.
Roost, Dano, et al. “Improving Sample Efficiency and Multi-Agent Communication in RL-Based Train Rescheduling.” Proceedings of the 7th SDS, IEEE, 2020, https://doi.org/10.21256/zhaw-19978.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.