id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
easat-9471	Jeon, Hwi; Lee, Chan-Ho; Choi, Jong-Geun; Kwon, Hyuk-Jin	Optimizing collaborative filtering recommender systems with the GRPO reinforcement learning algorithm	2025	11	.pdf	application/pdf	5219	303	45	This suggests that the policy gradient update process for item and positional embeddings in sequential collaborative filtering models may differ from that in graph and integrated models. Along with research on integrating collaborative filtering models, research on recommender systems utilizing reinforcement learning [9, 10] is also continuing.	cache/easat-9471.pdf	txt/easat-9471.txt