id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
fcis-6348	Yan, Dandan	Research on Reinforcement Learning Explainable Strategies Based on Advantage Saliency	2023	6	.pdf	application/pdf	4818	255	53	In this paper, we use the perturbation-based saliency map method, propose the use of advantage function to replace the existing method of calculating state saliency, realize the combination of advantage function and perturbation-based saliency map. [8]utilize the difference of value function and policy vector between original state and perturbed state to generate saliency map, Iyer et al.	cache/fcis-6348.pdf	txt/fcis-6348.txt