Causal Bandits: Learning Good Interventions via Causal Inference
Causal Bandits: Learning Good Interventions via Causal Inference
复制标题
因果强盗：通过因果推理学习良好的干预措施
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Mark D. Reid
中科院分区：
文献类型：
--
作者：
Finnian Lattimore;Tor Lattimore;Mark D. Reid
我们研究了使用因果模型来提高在随机环境中在线学习好的干预措施的速度的问题。我们的形式主义结合了多臂强盗和因果推理来建模一种未被现有方法利用的新型强盗反馈。我们提出了一种新的算法，它利用了因果反馈，并证明了其简单后悔的一个界，该界(在所有数量上)都严格优于不使用附加因果信息的算法。
We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm that exploits the causal feedback and prove a bound on its simple regret that is strictly better (in all quantities) than algorithms that do not use the additional causal information.