We offer an experimental benchmark and empirical study for off-policy policy evaluation
(OPE) in reinforcement learning, which is a key problem in many safety critical applications …

Reinforcement learning (RL) is one of the most vibrant research frontiers in machine
learning and has been recently applied to solve a number of challenging problems. In this …

Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline
datasets for both evaluating and selecting complex policies for decision making. The ability …

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision
policies without needing to conduct exploration, which is often costly or otherwise infeasible …

In this work, we consider the problem of model selection for deep reinforcement learning
(RL) in real-world environments. Typically, the performance of deep RL algorithms is …

Off-policy deep reinforcement learning (RL) has been successful in a range of challenging
domains. However, standard off-policy RL algorithms can suffer from several issues, such as …

Off-policy evaluation in reinforcement learning offers the chance of using observational data
to improve future outcomes in domains such as healthcare and education, but safe …

On-policy reinforcement learning (RL) algorithms have high sample complexity while off-
policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient …

Offline Reinforcement Learning promises to learn effective policies from previously-
collected, static datasets without the need for exploration. However, existing Q-learning and …

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that
uses standard supervised learning methods as subroutines. Our goal is an algorithm that …