Diversified Multinomial Logit Contextual Bandits
提出一种结合多项logit选择模型与多样性的上下文老虎机算法,在推荐系统中实现探索与多样性的平衡优化
arXiv:2607.11684v1 Announce Type: cross Abstract: Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the pot…