Metraipolis › archive › dc_253c540a7680

Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction — arXiv:2611.09371

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09371
License (as archived)
CC0-1.0
Archived
2026-11-09T22:35:00.624Z
SHA-256 of the archived text
6e3e1fa84d45e4e4b1d753235a37984e4c19f6c0318c4c77067d0388d4e61686
Stable URL of this page
https://metraipolis.com/documento/dc_253c540a7680

How to cite

Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction — arXiv:2611.09371 — arXiv (en), https://arxiv.org/abs/2611.09371 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_253c540a7680 (Metraipolis archive dc_253c540a7680, sha256 6e3e1fa84d45e4e4b1d753235a37984e4c19f6c0318c4c77067d0388d4e61686)
BibTeX
@misc{dc253c540a7680,
  title = {Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction — arXiv:2611.09371},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09371},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_253c540a7680; sha256 6e3e1fa84d45e4e4b1d753235a37984e4c19f6c0318c4c77067d0388d4e61686},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09371. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider offline imitation learning (IL), which aims to train an agent to imitate from the dataset of expert demonstrations without online interaction with the environment. Behavioral Cloning (BC) has been a simple yet effective approach to offline IL, but it is also well-known to be vulnerable to the covariate shift resulting from the mismatch between the state distributions induced by the learned policy and the expert policy. Moreover, as often occurs in practice, when expert datasets are collected from an arbitrary state distribution instead of a stationary one, these shifts become more pronounced, potentially leading to substantial failures in existing IL methods. Specifically, we focus on covariate shift resulting from arbitrary state data distributions, such as biased data collection or incomplete trajectories, rather than shifts induced by changes in dynamics or noisy expert actions. In this paper, to mitigate the effect of the covariate shifts in BC, we propose DrilDICE, which utilizes a distributionally robust BC objective by employing a stationary distribution correction ratio estimation (DICE) to derive a feasible solution. We evaluate the effectiveness of our method through an extensive set of experiments covering diverse covariate shift scenarios. The results demonstrate the efficacy of the proposed approach in improving the robustness against the shifts, outperforming existing offline IL methods in such scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.09371 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.327Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).