![Institutional Repository [SANDBOX]](images/dias.logo.png "Institutional Repository [SANDBOX]"){kind=logo}
Institutional Repository [SANDBOX]
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/10F634AF-6326-49E0-BD3F-78D66823D370 | - |
| Identifier | https://ebooks.iospress.nl/doi/10.3233/FAIA230304 | - |
| Identifier | https://doi.org/10.3233/FAIA230304 | - |
| Language | en | - |
| Extent | 8 pages | en |
| Title | Deep reinforcement learning with implicit imitation for lane-free autonomous driving | en |
| Creator | Chrysomallis Iason | en |
| Creator | Χρυσομαλλης Ιασων | el |
| Creator | Troullinos Dimitrios | en |
| Creator | Τρουλλινος Δημητριος | el |
| Creator | Chalkiadakis Georgios | en |
| Creator | Χαλκιαδακης Γεωργιος | el |
| Creator | Papamichail Ioannis | en |
| Creator | Παπαμιχαηλ Ιωαννης | el |
| Creator | Papageorgiou Markos | en |
| Creator | Παπαγεωργιου Μαρκος | el |
| Publisher | IOS Press | en |
| Description | The research leading to these results has received funding from the European Research Council under the European Union’s Horizon 2020 Research and Innovation programme/ ERC Grant Agreement n. [833915], project TrafficFluid. | en |
| Content Summary | Implicit imitation assumes that learning agents observe only the state transitions of an agent they use as a mentor, and try to recreate them based on their own abilities and knowledge of their environment. In this paper, we put forward a deep implicit imitation Q-network (DIIQN) model, which incorporates ideas from three well-known Deep Q-Network (DQN) variants. As such, we enable a novel implicit imitation method for online, model-free deep reinforcement learning. Our thorough experimentation in the complex environment of the emerging lane-free traffic paradigm, verifies the benefits of our approach. Specifically, we show that deep implicit imitation RL dramatically accelerates the learning process when compared to a “vanilla” DQN method; and, unlike explicit imitation reinforcement learning, it is able to outperform mentor performance without resorting to additional information, such as the mentor’s actions. | en |
| Type of Item | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Type of Item | Conference Full Paper | en |
| License | http://creativecommons.org/licenses/by-nc-nd/4.0/ | en |
| Date of Item | 2024-06-28 | - |
| Date of Publication | 2023 | - |
| Subject | Deep reinforcement learning | en |
| Subject | Implicit imitation | en |
| Subject | Lane-free traffic | en |
| Subject | Autonomous driving | en |
| Bibliographic Citation | I. Chrysomallis, D. Troullinos, G. Chalkiadakis, I. Papamichail and M. Papageorgiou, “Deep reinforcement learning with implicit imitation for lane-free autonomous driving,” in ECAI 2023 - Proc. of the 26th European Conference on Artificial Intelligence, vol. 372, Frontiers in Artificial Intelligence and Applications, K. Gal, A. Nowé, G. J. Nalepa, R. Fairstein, R. Rădulescu, Eds., Amsterdam, The Netherlands: IOS Press, 2023, pp. 461-468, doi: 10.3233/faia230304. | en |
Copyright © DIAS 2013
