Block Optimism for Nonstationary Bandits with Latent Linear Dynamics

2026-10-02，arXiv 发表统计学/机器学习论文《Block Optimism for Nonstationary Bandits with Latent Linear Dynamics》。该研究针对非平稳随机 bandit 问题，提出 Block Optimism 方法，处理动作同时影响即时奖励与未观测潜在状态演化的场景。目前仅有一手报道，无早期版本可供对比。

Generated from reports · updated 3 hr ago

There is not enough continuous observation data to draw a trend yet.