20.500.12556/RUL-103017 FighterZero : pristop samo-igranja za učenje igranja pretepaške igre z globokim spodbujevalnim učenjem magistrsko delo FighterZero: a self-playing deep reinforcement learning agent for fighting game AI Področje globokega učenja je v zadnjem desetletju doživelo precejšen razcvet. Uporablja se za reševanje premnogih problemov, v zadnjih petih letih pa precej tudi za igranje iger. Dva pomembna dosežka sta bila globoke Q-mreže (DQN) in AlphaZero. DQN se je naučila igrati klasične igre za Atari 2600 (Pong, Space Invaders, itd.), AlphaZero pa se je s samo-igranjem naučil igrati šah, šogi in Go. Mi smo na temelju AlphaZero poskusili zgraditi agenta FighterZero, ki bi se prav tako s samo-igranjem naučil igrati pretepaške računalniške igre. Rezultati so bili manj uspešni, kot smo pričakovali, saj se je časovna zahtevnost izkazala za nepremagljivo oviro. Deep learning has been a field of great academic interest and substantial breakthroughs over the last decade. Its applications are many and over the last five years it has spread also to the field of game playing, owing largely to two chief accomplishments of Google's DeepMind team: Deep Q-Networks (DQN), which learned to play classic Atari 2600 games, and AlphaZero, which learned, strictly through self-play, to play the board games chess, shogi and Go. In this thesis we attempted to build on the success of AlphaZero by adapting its self-playing architecture to fighting games, a popular genre of video games. The results were, however, less successful than we had expected and hoped, as the time constraints proved to be an insurmountable obstacle. umetna inteligenca inteligentni agent igre samo-igranje globoko učenje spodbujevalno učenje drevesno preiskovanje Monte Carlo nevronske mreže razvoj iger artificial intelligence intelligent agent games self-playing deep learning reinforcement learning Monte Carlo tree search neural networks game development true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2018-09-13 07:46:20 2018-09-13 07:46:24 2024-05-29 14:13:01 0000-00-00 00:00:00 2018 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004 90024 18432089 247.pdf 247.pdf 1 B1CCC1B688CBCDCF8FE337035F147355 9f0c43d0f020bfea339249af6a285b2a707e98e44d303e8b037ba070bb8c643b b02dd403-a1b5-11eb-a523-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=113400 Fakulteta za matematiko in fiziko Fakulteta za računalništvo in informatiko 0 0 0