Many reinforcement learning algorithms use trajectories collected from the execution of one
or more policies to propose a new policy. Because execution of a bad policy can be costly or …

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 …

Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of
offline pretrained policy using only a few online samples. Built on offline RL algorithms, most …

Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the
online deployment. However, during the real-time serving, we observe varieties of …

Most reinforcement learning practitioners evaluate their policies with online Monte Carlo
estimators for either hyperparameter tuning or testing different algorithmic design choices …

Off-policy evaluation (OPE) is crucial for evaluating a target policy's impact offline before its
deployment. However, achieving accurate OPE in large state spaces remains challenging …

In practice, it is essential to compare and rank candidate policies offline before real-world
deployment for safety and reliability. Prior work seeks to solve this offline policy ranking …

Off-policy reinforcement learning (RL) has achieved notable success in tackling many
complex real-world tasks, by leveraging previously collected data for policy learning …

The problem of off-policy evaluation (OPE) has long been advocated as one of the foremost
challenges in reinforcement learning. Gradient-based and emphasis-based temporal …