arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.02707cs.LGstat.ML
收藏

概率触发多臂组合强盗的Thompson抽样分析

Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms

Bilkent University(比尔肯特大学)

Alihan Hüyük, Cem Tekin

摘要:

分析了在半强盗反馈条件下,具有概率触发臂的组合多臂强盗的组合Thompson采样(CTS)的后悔性。我们假设学习者可以访问精确的优化预言,但事先不知道预期的基本臂结果。当期望回报函数在期望基臂结果上是Lipschitz连续时,我们推导了CTS的$O(\sum_{i =1}^m \log T / (p_i Δ_i))$后悔界,其中$m$表示基臂数目,$p_i$表示基臂$i$的最小非零触发概率,$Δ_i$表示基臂$i$的最小次优间隙.我们还比较了CTS与组合置信上界(CUCB)通过级联强盗问题的数值实验。

英文摘要:

We analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting. We assume that the learner has access to an exact optimization oracle but does not know the expected base arm outcomes beforehand. When the expected reward function is Lipschitz continuous in the expected base arm outcomes, we derive $O(\sum_{i =1}^m \log T / (p_i Δ_i))$ regret bound for CTS, where $m$ denotes the number of base arms, $p_i$ denotes the minimum non-zero triggering probability of base arm $i$ and $Δ_i$ denotes the minimum suboptimality gap of base arm $i$. We also compare CTS with combinatorial upper confidence bound (CUCB) via numerical experiments on a cascading bandit problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑