20.500.12556/DKUM-78061 Strojno učenje računalniškega igralca v igri Havannah diplomsko delo Machine learning of computer player in Havannah game V zadnjih letih je bil na področju umetne inteligence z uporabo okrepitvenega učenja nevronskih mrež dosežen preboj pri sposobnostih računalnika za igranje iger na deski, kot je Go, pri katerih je bil človek doslej močnejši nasprotnik. V diplomskem delu raziščemo algoritem igranja iger AlphaZero, ki kombinira tehnike preiskovanja dreves Monte Carlo in okrepitvenega učenja nevronskih mrež. Algoritem začne brez posebnega predznanja o dobrih strategijah, vendar se moč algoritma s postopkom učenja, ki se ponavlja iterativno, konstantno povečuje. V diplomskem delu opišemo in implementiramo osnovno obliko AlphaZero za igranje igre Havannah. Naučimo več različic modela nevronskih mrež, kjer vsak naslednik premaga svojega prednika in postane prvak. S tem pokažemo, da se lahko računalniški igralec uči igranja igre Havannah samo s podanimi pravili igre, tako da je sposoben premagati povprečnega človeškega igralca. In recent years, in the field of artificial intelligence, the reinforcement learning of neural networks has been used to achieve a breakthrough in the ability of the computer players to play board games, such as Go, in which human has been a stronger opponent. In this thesis, we explore the AlphaZero algorithm, which combines Monte Carlo tree search and reinforced neural network learning. The algorithm starts without any special prior knowledge of good strategies, but the algorithm becomes stronger with a learning process that repeats iteratively. In this thesis, we implement the basic form of AlphaZero for playing the Havannah game. Several versions of the neural network model are trained to play the game, where each successor defeats its predecessor and becomes the champion, thus showing that a computer player can learn to play the Havannah game and win against a human player, simply by being given the rules of the game and not possessing any special prior knowledge of good strategies. igra Havannah drevesno preiskovanje Monte Carlo nevronske mreže okrepitveno učenje tabula rasa Havannah Monte Carlo tree search neural networks reinforced learning tabula rasa true true false [N. Serec] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2020-10-14 09:01:38 2020-11-11 12:43:18 2022-08-09 17:32:01 2021-01-06 03:22:09 2020 0 Maribor 0 Maribor VIII, 42 f. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.388.4:004.85(043.2) 45050627 URN:SI:UM:DK:HGVJIGUO UN_Serec_Nino_2020.pdf UN_Serec_Nino_2020.pdf 1 42F2B3031EB6FB090511A641560D4F62 f71c3dfd7e853d8b1b85e666ccc19bd63b9171c8e8442764476c6629ba72668a f7b325bc-7c11-11eb-bb7a-00155d0001ca 20.500.12556/dkum/7fe92ae5-9424-4c6b-a043-81cad234730a https://dk.um.si/Dokument.php?lang=slv&id=147153 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0