The multi-armed bandit problemA large number of statistical decision problems in the social sciences and beyond can be framed as a (contextual) multi-armed bandit problem – a specific type of reinforcement learning problem. However, it is notoriously hard to develop and evaluate policies that tackle these types of problems, and to use such policies in applied studies. To address this issue, we have developed StreamingBandit, a python web application for developing and testing bandit policies in field studies. StreamingBandit can sequentially select treatments using (online) policies in real time. Once StreamingBandit is implemented in an applied context, different policies can be tested, altered, nested, and compared. StreamingBandit makes it easy to apply a multitude of bandit policies for sequential allocation in field experiments, and allows for the quick development and re-use of novel policies.
In his talk, Jules will first introduce the multi-armed bandit problem and its hurdles, and show examples of policies, after which he will detail the implementation logic of StreamingBandit> and provide several examples of its use.