Papers I Read

约 58 个字 预计阅读时间不到 1 分钟

Table of Contents

• 1. 「KDD'2025」Achieving Nearly-Optimal Regret and Sample Complexity in Dueling Bandits with Applications in Online Recommendations
• 2.「JMLR'2006」Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems
• 3.「ICML'2017」Dueling Bandits with Weak Regret
• 4.Welcome to the Era of Experience
• 5.「ICLR'2023」
• 6.「NIPS'2016」Generative Adversarial Imitation Learning