Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Deep reinforcement learning in strategic board game environments

Xenou Konstantia, Chalkiadakis Georgios, Afantenos, Stergos, 1978-...., enseignant-chercheur en informatique

Πλήρης Εγγραφή


URI: http://purl.tuc.gr/dl/dias/62B998F8-AF43-4440-A3D9-43A04588D7C4
Έτος 2019
Τύπος Κεφάλαιο σε Βιβλίο
Άδεια Χρήσης
Λεπτομέρειες
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 https://doi.org/10.1007/978-3-030-14174-5_16
Εμφανίζεται στις Συλλογές

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.

Υπηρεσίες

Στατιστικά