Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/62B998F8-AF43-4440-A3D9-43A04588D7C4 | - |
| Αναγνωριστικό | https://doi.org/10.1007/978-3-030-14174-5_16 | - |
| Αναγνωριστικό | https://link.springer.com/chapter/10.1007/978-3-030-14174-5_16 | - |
| Γλώσσα | en | - |
| Μέγεθος | 16 pages | en |
| Τίτλος | Deep reinforcement learning in strategic board game environments | en |
| Δημιουργός | Xenou Konstantia | en |
| Δημιουργός | Ξενου Κωνσταντια | el |
| Δημιουργός | Chalkiadakis Georgios | en |
| Δημιουργός | Χαλκιαδακης Γεωργιος | el |
| Δημιουργός | Afantenos, Stergos, 1978-...., enseignant-chercheur en informatique | en |
| Εκδότης | Springer Nature | en |
| Περίληψη | In this paper we propose a novel Deep Reinforcement Learning (DRL) algorithm that uses the concept of “action-dependent state features”, and exploits it to approximate the Q-values locally, employing a deep neural network with parallel Long Short Term Memory (LSTM) components, each one responsible for computing an action-related Q-value. As such, all computations occur simultaneously, and there is no need to employ “target” networks and experience replay, which are techniques regularly used in the DRL literature. Moreover, our algorithm does not require previous training experiences, but trains itself online during game play. We tested our approach in the Settlers Of Catan multi-player strategic board game. Our results confirm the effectiveness of our approach, since it outperforms several competitors, including the state-of-the-art jSettler heuristic algorithm devised for this particular domain. | en |
| Τύπος | Κεφάλαιο σε Βιβλίο | el |
| Τύπος | Book Chapter | en |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2020-10-29 | - |
| Ημερομηνία Δημοσίευσης | 2019 | - |
| Θεματική Κατηγορία | Deep Reinforcement Learning | en |
| Θεματική Κατηγορία | Strategic board games | en |
| Θεματική Κατηγορία | Neural network | en |
| Βιβλιογραφική Αναφορά | K. Xenou, G. Chalkiadakis and S. Afantenos, "Deep reinforcement learning in strategic board game environments," in Multi-Agent Systems. EUMAS 2018, vol. 11450, Lecture Notes in Computer Science, M. Slavkovik, Ed., Cham, Switzerland: Springer Nature, 2019, pp. 233-248. doi: 10.1007/978-3-030-14174-5_16 | en |
| Τίτλος Βιβλίου | Multi-Agent Systems. EUMAS 2018 | en |
| Σειρά Βιβλίου | Lecture Notes in Computer Science | en |
Copyright © DIAS 2013
