Pregled bibliografske jedinice broj: 1187388
Anticheat System Based on Reinforcement Learning Agents in Unity
Anticheat System Based on Reinforcement Learning Agents in Unity // Information, 13 (2022), 4; 173, 12 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1187388 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Anticheat System Based on Reinforcement Learning
Agents in Unity
Autori
Lukaš, Mihael ; Tomičić, Igor ; Bernik, Andrija
Izvornik
Information (2078-2489) 13
(2022), 4;
173, 12
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
security ; artificial intelligence ; infosec ; reinforcement learning ; agents ; games ; gaming ; unity
Sažetak
Game cheating is a common occurrence that may degrade the experience of “honest” players. It can be hindered by using appropriate anticheat systems, which are being considered as a subset of security-related issues. In this paper, we implement and test an anticheat system whose main goal is to help differentiate human players from AI players. For this purpose, we first developed a multiplayer game inside game engine Unity that would serve as a framework for training the reinforcement learning agent. This agent would thus learn to differentiate human players from bots within the game. We implemented the Machine Learning Agents Toolkit library, which uses the proximal policy optimization algorithm. AI players are implemented using state machines, and perform certain actions depending on which condition is satisfied. Two experiments were carried out for testing the agent and showed promising results for identifying artificial players.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Projekti:
UNIN--UNIN-DRUŠ-21-1-6 - Utjecaj senzorske mehanike, audio impulsa te dubinskih mapa na uživanje, pažnju i percepciju korisnika (nastavak predistraživanja i analiza rezultata) (SMAI-Z) (Bernik, Andrija, UNIN ) ( CroRIS)
Ustanove:
Fakultet organizacije i informatike, Varaždin,
Sveučilište Sjever, Koprivnica
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Emerging Sources Citation Index (ESCI)
- Scopus