Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/10F634AF-6326-49E0-BD3F-78D66823D370 | - |
| Αναγνωριστικό | https://ebooks.iospress.nl/doi/10.3233/FAIA230304 | - |
| Αναγνωριστικό | https://doi.org/10.3233/FAIA230304 | - |
| Γλώσσα | en | - |
| Μέγεθος | 8 pages | en |
| Τίτλος | Deep reinforcement learning with implicit imitation for lane-free autonomous driving | en |
| Δημιουργός | Chrysomallis Iason | en |
| Δημιουργός | Χρυσομαλλης Ιασων | el |
| Δημιουργός | Troullinos Dimitrios | en |
| Δημιουργός | Τρουλλινος Δημητριος | el |
| Δημιουργός | Chalkiadakis Georgios | en |
| Δημιουργός | Χαλκιαδακης Γεωργιος | el |
| Δημιουργός | Papamichail Ioannis | en |
| Δημιουργός | Παπαμιχαηλ Ιωαννης | el |
| Δημιουργός | Papageorgiou Markos | en |
| Δημιουργός | Παπαγεωργιου Μαρκος | el |
| Εκδότης | IOS Press | en |
| Περιγραφή | 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 |
| Περίληψη | 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 |
| Τύπος | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Τύπος | Conference Full Paper | en |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by-nc-nd/4.0/ | en |
| Ημερομηνία | 2024-06-28 | - |
| Ημερομηνία Δημοσίευσης | 2023 | - |
| Θεματική Κατηγορία | Deep reinforcement learning | en |
| Θεματική Κατηγορία | Implicit imitation | en |
| Θεματική Κατηγορία | Lane-free traffic | en |
| Θεματική Κατηγορία | Autonomous driving | en |
| Βιβλιογραφική Αναφορά | 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
