20.500.12556/DKUM-80671 Globoko okrepitveno učenje za igranje iger na podlagi video vhoda magistrsko delo Deep reinforcement learning for playing games based on video input V magistrskem delu smo se ukvarjali z okrepitvenim učenjem agentov za igranje računalniških iger. V ta namen smo implementirali tri modele agenta, ki temeljijo na uporabi nevronske mreže za aproksimacijo funkcije vrednosti akcij, in predlagali lastno izboljšano arhitekturo dvobojevalne dvojne Q-mreže. Učenje smo izvajali na igrah Pong in Beamrider iz nabora iger Atari 2600. Ugotovili smo, da z našim pristopom dosežemo boljšo zmogljivost agenta kot globoka Q-mreža, dvojna globoka Q-mreža in dvojna globoka Q-mreža z dvobojevalno arhitekturo v igri Pong, medtem ko se v igri Beamrider agent uči počasneje, predvidoma zaradi šuma v drugačni predstavitvi stanja, ki ga predlagani model uporablja. In the master's thesis, we dealt with reinforcement learning of agents for playing computer games. To this end, we implemented three agent models based on the use of neural networks as action value function approximators, and proposed our own improved architecture of the dueling double Q-network. We conducted the training on the games Pong and Beamrider from the Atari 2600 games. We found that with our approach we achieve better agent performance than deep Q-networks, double deep Q-networks and double deep Q-networks with dueling architecture in the game Pong, while in Beamrider the agent learns more slowly, presumably due to the noise in the different representation of the state used by the proposed model. globoko okrepitveno učenje nevronske mreže globoka Q-mreža dvobojevalna arhitektura igre Atari Pong Beamrider deep reinforcement learning neural networks deep Q-network dueling architecture Atari games Pong Beamrider true true false M. Bozhinova] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2021-09-28 00:37:32 2021-10-20 06:22:42 2022-08-09 23:47:11 0000-00-00 00:00:00 2021 0 Maribor 0 Maribor XII, 52 str. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85:004.96(043.2) 83074563 MAG_Bozhinova_Monika_2021.pdf MAG_Bozhinova_Monika_2021.pdf 1 A8555C713D5D6B97A0BAA03C1473C248 da12dcab4c30992731aafaf88f942b5032ee5c2119eb0135dba03222fdb03ee8 fc96cb04-202c-11ec-8d04-00155d000105 20.500.12556/dkum/5d9a358e-6fb9-42ab-973f-584c0d32e4a4 https://dk.um.si/Dokument.php?lang=slv&id=154570 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0