20.500.12556/DKUM-79190 Okrepitveno učenje agentov za igranje iger v pogonu Unity magistrsko delo Reinforcement learning of game-playing agents in the Unity engine V magistrskem delu obravnavamo algoritme okrepitvenega učenja na primeru igranja računalniških iger. Namen magistrskega dela je implementacija igre v okolju Unity in analiza učinkovitosti algoritmov okrepitvenega učenja računalniškega igralca. Opisane so teoretične osnove okrepitvenega učenja, podrobneje pa so predstavljeni algoritmi PPO (angl. Proximal Policy Optimization), SAC (angl. Soft Actor Critic) in DQN (angl. Deep Q-Network), ki so uporabljeni v končni analizi. Rezultati so pokazali, da je bilo učenje agenta v celoti gledano uspešno. V testnem okolju se je najbolje odrezal algoritem PPO, z uporabo katerega je naučen agent v povprečju dosegal 86,4% maksimalne možne nagrade, najslabše pa algoritem DQN, ki ni primeren za uporabo v implementiranem testnem okolju. In the master thesis we deal with the reinforcement learning algorithms on the example of playing computer games. The purpose of the thesis is to implement a game in the Unity engine and perform an effectiveness analysis of reinforcement learning algorithms of a computer player. Theoretic bases of reinforcement learning are described and PPO (Proximal Policy Optimization), SAC (Soft Actor Critic) and DQN (Deep Q-Network) algorithms that are used in the final analysis are presented in detail. The results have shown that the learning of the agent was overall successful. The best algorithm in the test environment was PPO, using which the agent achieved 86,4% of the maximal possible reward on average, and the worst was DQN, which is not suitable for use in the implemented test environment. okrepitveno učenje računalniške igre Unity agent strojno učenje reinforcement learning computer games Unity agent machine learning true true false [J. Banko] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2021-05-24 21:20:38 2021-06-17 13:56:27 2022-08-09 20:15:12 0000-00-00 00:00:00 2021 0 Maribor 0 Maribor VIII, 53 str. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85:004.96(043.2) 67936771 MAG_Banko_Jan_2021.pdf MAG_Banko_Jan_2021.pdf 1 3810EF09BE2C2E4258C058D984F69B2C f34e5408a6fbd492550a9b3beab4df12277e35ba8ffec5002763adf507f348f1 09bd8c03-bcc6-11eb-97c7-00155d581298 20.500.12556/dkum/f2dcb1b3-f075-4fe7-88ee-9ccbdb9b9f98 https://dk.um.si/Dokument.php?lang=slv&id=150358 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0