Offline Reinforcement Learning with Realizability and Single-policy Concentrability. (arXiv:2202.04634v3 [cs.LG] UPDATED)

Sample-efficiency guarantees for offline reinforcement learning (RL) often
rely on strong assumptions on both the function classes (e.g.,
Bellman-completeness) and the data coverage (e.g., all-policy concentrability).
Despite the recent efforts on relaxing these assumptions, existing works are
only able to relax one of the two factors, leaving the strong assumption on the
other factor intact. As an important open problem, can we achieve
sample-efficient offline RL with weak assumptions on both factors?

In this paper we answer the question in …

arxiv learning lg policy reinforcement reinforcement learning