Variational OOD State Correction for Offline Reinforcement Learning

Ke Jiang; Wen Jiang; Xiaoyang Tan

AAAI 2026technical0 citations

Variational OOD State Correction for Offline Reinforcement Learning

Abstract

The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. However, previous methods correct the agent

BibTeX

@inproceedings{aaai2026_variationaloodst,
  title = {Variational OOD State Correction for Offline Reinforcement Learning},
  author = {Ke Jiang and Wen Jiang and Xiaoyang Tan},
  booktitle = {AAAI 2026},
  year = {2026}
}