When is Offline Policy Selection Feasible for Reinforcement Learning?Jan 4, 2023·Vincent Liu,Prabhat Nagarajan,Andrew Patterson,Martha White· 0 min read Cite URLTypeConference paperPublicationUnder submissionLast updated on Jan 4, 2023 AuthorsVincent LiuPostdoctoral Research and Teaching Fellow ← Investigating the properties of neural network representations in reinforcement learning Jan 1, 2024Exploiting action impact regularity and exogenous state variables for offline reinforcement learning Jan 3, 2023 →
