Metraipolis › archive › dc_b2dda2e32ce2
ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RL — arXiv:2611.02177
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02177
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:19:44.014Z
- SHA-256 of the archived text
396ebf39d7d4ecd6fddbcca8c334052b83709ebf3ef1ee0f7d1dd8a095a9d177- Stable URL of this page
https://metraipolis.com/documento/dc_b2dda2e32ce2
How to cite
ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RL — arXiv:2611.02177 — arXiv (en), https://arxiv.org/abs/2611.02177 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2dda2e32ce2 (Metraipolis archive dc_b2dda2e32ce2, sha256 396ebf39d7d4ecd6fddbcca8c334052b83709ebf3ef1ee0f7d1dd8a095a9d177)
BibTeX
@misc{dcb2dda2e32ce2,
title = {ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RL — arXiv:2611.02177},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02177},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2dda2e32ce2; sha256 396ebf39d7d4ecd6fddbcca8c334052b83709ebf3ef1ee0f7d1dd8a095a9d177},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02177. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Offline-to-online reinforcement learning (RL) follows the pretrain-finetune paradigm: an agent is first pretrained on historical data and then adapted through online interaction. We study offline-to-online adaptation without offline replay, where the agent must improve using only the pretrained model and newly collected experience. A key challenge is to avoid catastrophic failure, a sharp early performance collapse during online fine-tuning, while still achieving strong asymptotic performance. Through controlled experiments, we show that removing offline replay can induce catastrophic failure, while retaining strong conservative regularization from offline RL can suppress final online performance. We also find that common stabilization strategies do not reliably prevent early collapse, and that the critic-side mechanisms we test are insufficient on their own. Motivated by these findings, we propose ANCHOR, a simple adaptation method that anchors the actor to the offline-pretrained policy early in online fine-tuning, anneals this constraint over time, and retains only a small residual conservative critic regularizer. We provide a theoretical interpretation showing that KL anchoring helps preserve critic reliability across nearby occupancy distributions, with a two-phase regret bound explaining when anchoring should be maintained or relaxed. Across FrankaKitchen, AntMaze, and Adroit tasks, ANCHOR substantially reduces catastrophic failure while maintaining strong asymptotic performance. Ablations show that KL annealing and the residual conservative weight are important for balancing early stability and online adaptation, while additional analysis shows that ANCHOR is most beneficial when the pretrained policy contains useful behavior to preserve. Code is available at this https URL . 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/2611.02177 — 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 2026-11-03T18:09:53.663Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).