20.500.12556/RUL-72425 Agenti za simulacijo človeškega obnašanja v svetu igre Simulating human-like behaviour in games using intelligent agents Področje umetne inteligence v zadnjem času zelo napreduje, pristopi pod-roč-ja pa se uporabljajo tudi za računalniško vodenje likov v svetu igre. Pojem inteligentnih agentov nam omogoči dobro teoretično podlago za izbiro najprimernejših pristopov za dosego racionalnega obnašanja teh likov. Z dodatkom omejitev na agentove sposobnosti pa dobimo res človeku podobno vedenje. V diplomskem delu smo predstavili in med seboj primerjali različne tipe agentov, ki se v igrah (a ne le v igrah) v ta namen uporabljajo ter predstavili, kako se omejitev sposobnosti implementira v svet igre. Cilj diplomskega dela je prikazati dobre in slabe lastnosti vsakega od agentov in ugotoviti, za izvedbo kakšnih nalog je primeren. Pokazali smo, da so že preprosti agenti lahko povsem primerni za določene naloge, za bolj zahtevne pa agenti pogosto potrebujejo bolj napredne pristope. Ugotovili smo, da na obnašanje najbolj vpliva dodatek ciljne usmerjenosti agentov, poleg nje pa je v veliko pomoč tudi pristop avtomata s stanji. The field of artificial intelligence has come a long way in the past 50 years, and studies of its methods soon expanded to a field in which they are of great practical value -- computer games. The concept of intelligent agents provides a much needed theoretical background for the comparison of various different approaches to intelligent, rational behaviour of computer-controlled characters in games. By combining rationality with certain limitations of the capabilities of our agents, we can achieve very human-like behaviour. In this diploma thesis we introduced and compared various types of agents that are used in games (but not only in games) and showed how to implement meaningful, reasonable limitations to agent capabilities into the game world. The aim of this thesis is to show the strengths and weaknesses of each type of agent and decide what types of tasks it is suitable for. We showed that even the simplest agents can succeed in their tasks in certain task environments, while more difficult task environments often require a more advanced agent architecture. The addition of goals into the agent architecture had the biggest impact on the agent's behaviour, while the finite-state machine approach kept our implementation simple and compact. agent inteligenca umetna inteligenca igre svet igre razvoj iger agent intelligence rationality artificial intelligence games game world game development true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2015-09-17 11:20:07 2015-09-17 11:20:08 2022-08-01 15:59:31 0000-00-00 00:00:00 2015 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1970-01-01 16405 Vitek_Matej_-_Agenti_za_simulacijo_cloveskega_obnasanja_v_svetu_igre.pdf Vitek_Matej_-_Agenti_za_simulacijo_cloveskega_obnasanja_v_svetu_igre.pdf 1 729210851337FC011E96CFE78920C691 5dfeddcf037eecececdb23680a0d1bfb39c6f65f829b9bbf77fca0b7e4ba6e85 5c167aeb-a1ad-11eb-a523-00155dcfd717 20.500.12556/rul/6cf6da62-9ac5-44ae-9e06-dc99f3efb5a2 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=72464 Fakulteta za računalništvo in informatiko 0 0 0