Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm

arXiv:2507.05306v3 Announce Type: replace-cross Abstract: We consider the multinomial logistic bandit problem in which a learner interacts with an environment by selecting actions to maximize expected rewards based on probabilistic feedback from multiple possible outcomes. In ...

🔗 Read more: https://arxiv.org/abs/2507.05306

#News #Software #Environment #Policy #AI #Space #Academic