The current success of RL highly relies on excessive amount ofdata, which, however,isusually not available inmanyreal world tasks wheredeploying anew policyisverycostlyorevenrisky.

Methods for sequential decision making are often built upon a foundational assumption that the underlying decision process is stationary [Sutton and Barto, 2018]. While this assumption was a cornerstone when laying the theoretical foundations of the field, and while is often reasonable, it isseldom trueinpractice andcanbeunreasonable [Dulac-Arnold etal.,2019].

The world currently offers an abundance of data in multiple domains, from which we can learn reinforcement learning (RL) policies without further interaction with the environment. RL agents learning offline from such data is possible but deploying them while learning might be dangerous in domains where safety is critical. Therefore, it is essential to find a way to estimate how a newly-learned agent will perform if deployed in the target environment before actually deploying it and without the risk of overestimating its true performance. To achieve this, we introduce a framework for safe evaluation of offline learning using approximate high-confidence off-policy evaluation (HCOPE) to estimate the performance of offline policies during learning. In our setting, we assume a source of data, which we split into a train-set, to learn an offline policy, and a test-set, to estimate a lower-bound on the offline policy using off-policy evaluation with bootstrapping. A lower-bound estimate tells us how good a newly-learned target policy would perform before it is deployed in the real environment, and therefore allows us to decide when to deploy our learned policy.

In this paper, we propose a framework for using reinforcement learning (RL) algorithms to learn good policies for personalized ad recommendation (PAR) systems. The RL algorithms take into account the long-term effect of an action, and thus, could be more suitable than myopic techniques like supervised learning and contextual bandit, for modern PAR systems in which the number of returning visitors is rapidly growing. However, while myopic techniques have been well-studied in PAR systems, the RL approach is still in its infancy, mainly due to two fundamental challenges: how to compute a good RL strategy and how to evaluate a solution using historical data to ensure its "safety" before deployment. In this paper, we propose to use a family of off-policy evaluation techniques with statistical guarantees to tackle both these challenges. We apply these methods to a real PAR problem, both for evaluating the final performance and for optimizing the parameters of the RL algorithm. Our results show that a RL algorithm equipped with these off-policy evaluation techniques outperforms the myopic approaches. Our results also give fundamental insights on the difference between the click through rate (CTR) and life-time value (LTV) metrics for evaluating the performance of a PAR algorithm.