Skripsi

IMPLEMENTASI REINFORCEMENT LEARNING PADA AGEN PENGHINDAR HALANGAN OTOMATIS DALAM GAME ENDLESS RUNNER

---

With technological advancements, the application of Artificial Intelligence (AI) has been widely adopted across various industries, including the gaming industry. In games, AI can be used to procedurally generate content, analyze user behavior, and develop AI agents. This study aims to develop and evaluate an AI agent capable of independent learning and adaptation in an endless runner game environment. The research methodology includes the implementation of reinforcement learning with the Proximal Policy Optimization (PPO) algorithm to train the agent in making optimal decisions related to character movement for obstacle avoidance. Research results demonstrate that the AI agent performs well, successfully passing an average of 53 obstacles with a standard deviation ratio of 0.289 across 10 trials, and achieving 97% accuracy in navigating through 100 obstacles. This research This research can be the basis for developing AI in games and can be further developed into a multi-agent scenario, where two agents interact within the same environment but with different objectives.

---

Availability

Detail Information

Series Title

-

Call Number

T1817132025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 59 hlm.; ilus.; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Teknik Informatika
Kecerdasan Buatan .

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment