@article{ART003246031},
author={Junha Hwang},
title={Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={9},
pages={1-10}
TY - JOUR
AU - Junha Hwang
TI - Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 9
PB - The Korean Society Of Computer And Information
SP - 1
EP - 10
SN - 1598-849X
AB - Deep Q-Learning (DQL) is a representative deep reinforcement learning method. Deep Q-Network (DQN), based on DQL, has improved the performance by replaying past experiences stored in a replay memory. In the DQN, past experiences are randomly sampled from a single replay memory for training.
This paper proposes a heuristic-based approach using multiple replay memories to further enhance the performance of DQL. Specifically, experiences are categorized based on knowledge of the target problem and stored in their corresponding replay memories. During training, a fixed number of experiences are randomly sampled from each replay memory. The proposed method was applied to the Cart Pole, the Mountain Car, and the Ball Avoider problems, and comparative experiments were conducted to compare with existing methods. The experimental results show that the proposed method can significantly improve the performance of DQL.
KW - Reinforcement Learning;Deep Q-Learning;Deep Q-Network;Replay Memory;;Multiple Replay Memories
DO -
UR -
ER -
Junha Hwang. (2025). Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach. Journal of The Korea Society of Computer and Information, 30(9), 1-10.
Junha Hwang. 2025, "Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach", Journal of The Korea Society of Computer and Information, vol.30, no.9 pp.1-10.
Junha Hwang "Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach" Journal of The Korea Society of Computer and Information 30.9 pp.1-10 (2025) : 1.
Junha Hwang. Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach. 2025; 30(9), 1-10.
Junha Hwang. "Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach" Journal of The Korea Society of Computer and Information 30, no.9 (2025) : 1-10.
Junha Hwang. Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach. Journal of The Korea Society of Computer and Information, 30(9), 1-10.
Junha Hwang. Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach. Journal of The Korea Society of Computer and Information. 2025; 30(9) 1-10.
Junha Hwang. Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach. 2025; 30(9), 1-10.
Junha Hwang. "Enhanced Deep Q-Learning with Multiple Replay Memories: A Heuristic-Based Approach" Journal of The Korea Society of Computer and Information 30, no.9 (2025) : 1-10.
