Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : bulletin of computer science research

Analisis Visual Perilaku Agen Q-Learning dan SARSA pada Cliff Walking Problem dengan Explainable Reinforcement Learning Firas Atqiya; Muhammad Rizqi Sholahuddin
Bulletin of Computer Science Research Vol. 6 No. 2 (2026): February 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i2.984

Abstract

Reinforcement Learning (RL) has achieved remarkable success in complex sequential decision tasks. However, modern RL models often lack explainability, creating a serious "black box" problem, especially in high-stakes domains. This study proposes a Pygame-based real-time visualization architecture for RL, and demonstrates its benefits in a Cliff Walking case study using Q-Learning and SARSA algorithms. Key contributions include: (1) a real-time visualization architecture that decouples training logic from graphics rendering with support more than 60 FPS, (2) interpretive visualization techniques including diverging heatmaps, dynamic policy arrows, and Ghost Policies, and (3) a comprehensive empirical study clarifying the distinct characteristics of both algorithms. Experimental results clearly show that Q-Learning selects an efficient but risky path aligned with its optimistic off-policy nature, while SARSA converges on a safer path reflecting its on-policy nature that considers exploration safety. Quantitatively, Q-Learning successfully achieved an optimal 13-step path with an accumulation of 10,642 falls, whereas SARSA converged to a safe 23-step path with a significantly higher collision frequency (232,844 times) to avoid extreme penalties from the cliff zone.
Co-Authors Ade Hodijah Afrida Helen Agustiani, Amelia Dewi Ais Laksana Amelia Dewi Agustiani Aprianti Nanda Sari Ardhian Ekawijana Asri Maspupah Bakhrun, Akhmad Bima Putra Sudimulya Carolina Magdalena Lasambouw Daffa Muzhaffar Dewi, Yunita Citra Dhia Fauzan, Fachri Dimas Kurniawan Djoko Cahyo Utomo Lieharyani Djoko Cahyo Utomo Lieharyani Djoni Djatnika Eddy Bambang Soewono Elfada, Berliana Fachri Dhia Fauzan Fardan Al Jihad Farida Agoes FENNY MARTHA DWIVANY Firas Atqiya Firdaus, Lukmannul Hakim Gantini, Annisa Dinda Gelar, Trisna Gianluigi Julian Hayati, Hashri Husna Faridah Ihsani, Nisa Iwan Awaludin Jonner Hutahaean Kadhafi, Irvan Lukmannul Hakim Firdaus Maisevli Harika Maisevli Harika Maisevli Harika Malika, Adinda Faayza Meilinda, Lina Melinia, Gina Muhammad Riza Alifi Muhammad Samudera Mulia, Syelvie Ira Ratna Nugraha, Wili Akbar Nuri Nurianti Nurjannah Syakrani Nurjannah Syakrani Nuryati, Neneng Priyanto Hidayatullah Priyanto Hidayatullah, Priyanto Putri, Salsabila Maharani Putriadhinia, Salma Syawalan Rafli Fadhilah Refdinal Tubagus Salsabila Maharani Putri Santosa, Yoseph Sari, Aprianti Nanda Satryo Haryo Setiadi Rachmat Sitepu, Rezky Wahyuda Siti Dwi Setiarini Siti Dwi Setiarini Sofy Fitriani Sofy Fitriani SONY SUHANDONO Sudimulya, Bima Putra Suharsih, Ririn Syakrani, Nurjannah Topan Trianto Trisna Gelar Abdillah Vandha Pradiyasma Widarta Widarta, Vandha Pradiyasma Wisnuadhi, Bambang Wulan, Sri Ratna Yayang Setia Budi Yudi Widhiyasana Yunita Citra Dewi Yusuf Sofyan Yusuf Sofyan, Jurusan Teknik Elektro Politeknik Negeri Bandung, Parno Raharjo, Tria Maariz, Jurusan