Learning Macromanagement in Starcraft by Deep Reinforcement Learning

W Huang, Q Yin, J Zhang, K Huang - Sensors, 2021 - mdpi.com
StarCraft is a real-time strategy game that provides a complex environment for AI research.
Macromanagement, ie, selecting appropriate units to build depending on the current state, is …

Active player modeling in the iterated prisoner's dilemma

H Park, KJ Kim - Computational intelligence and neuroscience, 2016 - Wiley Online Library
The iterated prisoner's dilemma (IPD) is well known within the domain of game theory.
Although it is relatively simple, it can also elucidate important problems related to …

[PDF][PDF] TECHNIQUES D'APPRENTISSAGE PROFOND POUR LA MODÉLISATION DES USAGERS DANS LES SYSTÈMES INTERACTIFS D'APPRENTISSAGE …

AAN TATO - 2020 - archipel.uqam.ca
L'un des objectifs fondamentaux de la recherche sur l'interaction homme-machine est de
rendre les systèmes interactifs plus attrayants, utiles et d'offrir aux utilisateurs des …

AKILLI ETMENLER İLE IZGARA TABANLI BİR MOBİL OYUNDA YOL BULMA

S Utku, K Tilki - Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen …, 2018 - dergipark.org.tr
Büyük bir endüstri haline gelen oyun alanında, her alanda olduğu gibi yapay zekânın
kullanımı yaygınlaşmaktadır. Oyunlar da bulunan yapay zekâ oyuna karakterleri hareket …