arXivDaily arXiv每日学术速递 周一至周五更新

作者

Zhi-Hua Zhou

Machine Learning

2026-01-06 至 2026-01-06 共收录 1
2601.01069 2026-01-06 cs.LG stat.ML

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs

重新审视非平稳参数老虎机和MDP中的加权策略

Jing Wang, Peng Zhao, Zhi-Hua Zhou

AI总结 本文提出了一种简化分析框架,改进了非平稳参数老虎机和MDP的加权策略,提升了算法效率和遗憾界。

Comments accepted by IEEE Transactions on Information Theory. arXiv admin note: substantial text overlap with arXiv:2303.02691

详情

展开后加载摘要…

URL PDF HTML 收藏