Budgeted and Non-budgeted Causal Bandits

Budgeted and Non-budgeted Causal Bandits
复制标题

预算内和非预算的因果强盗

DOI:
--
复制
发表时间:
2020
期刊:
International Conference on Artificial Intelligence and Statistics
影响因子:
--
通讯作者:
Gaurav Sinha
Gaurav Sinha
中科院分区:
--
文献类型:
--
作者:
V. Nair;Vishakha Patil;Gaurav Sinha

文献摘要

参考文献

被引文献

相似文献

在因果图中学习好的干预可以建模为带有边信息的随机多臂强盗问题。首先,我们研究这个问题时,干预措施比观察更昂贵,并指定了预算。如果从可干预节点到奖励节点没有后门路径,那么我们提出了一种算法,以最小化简单的遗憾,最佳的权衡观察和干预的基础上的干预成本。我们还提出了一个算法,占干预措施的成本,利用因果边信息,并尽量减少预期的累积遗憾,而不超过预算。我们的累积遗憾最小化算法比不考虑边信息的标准算法性能更好。最后,我们研究了一般图中无预算约束的最佳干预措施的学习问题,并给出了一个算法,当每个干预措施的奖励变量的父分布已知时,该算法根据实例参数实现恒定的期望累积遗憾。我们的结果进行了实验验证,并在目前的文献中最知名的界限。
Learning good interventions in a causal graph can be modelled as a stochastic multi-armed bandit problem with side-information. First, we study this problem when interventions are more expensive than observations and a budget is specified. If there are no backdoor paths from an intervenable node to the reward node then we propose an algorithm to minimize simple regret that optimally trades-off observations and interventions based on the cost of intervention. We also propose an algorithm that accounts for the cost of interventions, utilizes causal side-information, and minimizes the expected cumulative regret without exceeding the budget. Our cumulative-regret minimization algorithm performs better than standard algorithms that do not take side-information into account. Finally, we study the problem of learning best interventions without budget constraint in general graphs and give an algorithm that achieves constant expected cumulative regret in terms of the instance parameters when the parent distribution of the reward variable for each intervention is known. Our results are experimentally validated and compared to the best-known bounds in the current literature.
DOI: --
发表时间: 2017
期刊: --
影响因子: --
作者:
Murat Kocaoglu;Karthikeyan Shanmugam;E. Bareinboim
通讯作者: Murat Kocaoglu;Karthikeyan Shanmugam;E. Bareinboim
结构性因果强盗:在哪里干预?
DOI: --
发表时间: 2018
期刊: Advances in Neural Information Processing Systems 31
影响因子: --
作者:
Lee, Sanghack;Bareinboim, Elias
通讯作者: Bareinboim, Elias
DOI: --
发表时间: 2020-05
期刊: --
影响因子: --
作者:
Raghavendra Addanki;S. Kasiviswanathan;A. Mcgregor;Cameron Musco
通讯作者: Raghavendra Addanki;S. Kasiviswanathan;A. Mcgregor;Cameron Musco