KJCKorea
Journal Central

@article{ART002967645},
author={Kyeongsoo Kim and Young-Sun Yun},
title={Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game},
journal={Journal of Software Assessment and Valuation},
issn={2092-8114},
year={2023},
volume={19},
number={2},
pages={49-59},
doi={10.29056/jsav.2023.06.06}

TY - JOUR
AU - Kyeongsoo Kim
AU - Young-Sun Yun
TI - Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game
JO - Journal of Software Assessment and Valuation
PY - 2023
VL - 19
IS - 2
PB - Korea Software Assessment and Valuation Society
SP - 49
EP - 59
SN - 2092-8114
AB - Game research applying reinforcement learning has demonstrated that AI can outperform humans. In this study, we extend this approach to '3D-Pinball', a game similar to 'Video Pinball' but with greater complexity. Three reinforcement learning algorithms - DQN, Double DQN, and Dueling Double DQN - are applied to both CNN-based models using visual data and MLP-based models extracting appropriate features from high-dimensional data. These are then evaluated in '3D-Pinball'. Restrictions on gameplay time and lives were implemented for efficient experimentation. Results showed that the Dueling Double DQN algorithm applied to the MLP-based model yielded the highest performance increase and game scores, underscoring the superior performance of simpler models in restricted environments. Consequently, it appears that model development considering constraints is required for superior performance in learning and game environments.
KW - Reinforcement Learning;Artificial Intelligence;Deep Learning;3D-Pinball;Preprocessing
DO - 10.29056/jsav.2023.06.06
ER -

Kyeongsoo Kim and Young-Sun Yun. (2023). Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game. Journal of Software Assessment and Valuation, 19(2), 49-59.

Kyeongsoo Kim and Young-Sun Yun. 2023, "Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game", Journal of Software Assessment and Valuation, vol.19, no.2 pp.49-59. Available from: doi:10.29056/jsav.2023.06.06

Kyeongsoo Kim, Young-Sun Yun "Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game" Journal of Software Assessment and Valuation 19.2 pp.49-59 (2023) : 49.

Kyeongsoo Kim, Young-Sun Yun. Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game. 2023; 19(2), 49-59. Available from: doi:10.29056/jsav.2023.06.06

Kyeongsoo Kim and Young-Sun Yun. "Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game" Journal of Software Assessment and Valuation 19, no.2 (2023) : 49-59.doi: 10.29056/jsav.2023.06.06

Kyeongsoo Kim; Young-Sun Yun. Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game. Journal of Software Assessment and Valuation, 19(2), 49-59. doi: 10.29056/jsav.2023.06.06

Kyeongsoo Kim; Young-Sun Yun. Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game. Journal of Software Assessment and Valuation. 2023; 19(2) 49-59. doi: 10.29056/jsav.2023.06.06

Kyeongsoo Kim, Young-Sun Yun. Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game. 2023; 19(2), 49-59. Available from: doi:10.29056/jsav.2023.06.06

Kyeongsoo Kim and Young-Sun Yun. "Performance Analysis of Reinforcement Learning Algorithms and Models Based on the 3D-Pinball Game" Journal of Software Assessment and Valuation 19, no.2 (2023) : 49-59.doi: 10.29056/jsav.2023.06.06