Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi

Anticheat System Based on Reinforcement Learning Agents in Unity (CROSBI ID 307816)

Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija

Lukaš, Mihael ; Tomičić, Igor ; Bernik, Andrija Anticheat System Based on Reinforcement Learning Agents in Unity // Information, 13 (2022), 4; 173, 12

Podaci o odgovornosti

Lukaš, Mihael ; Tomičić, Igor ; Bernik, Andrija

engleski

Anticheat System Based on Reinforcement Learning Agents in Unity

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.

security ; artificial intelligence ; infosec ; reinforcement learning ; agents ; games ; gaming ; unity

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o izdanju

13 (4)

2022.

173

12

objavljeno

2078-2489

Trošak objave rada u otvorenom pristupu

Povezanost rada

Informacijske i komunikacijske znanosti, Računarstvo

Poveznice
Indeksiranost