Metraipolis › archive › dc_336fcb1cdbf8
Value-Guided Repulsion for Offline Reinforcement Learning — arXiv:2610.20190
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20190
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:25.613Z
- SHA-256 of the archived text
c324dfc9f576074c7d7043cea870dda1c7200357fb24669160586a98cc422978- Stable URL of this page
https://metraipolis.com/documento/dc_336fcb1cdbf8
How to cite
Value-Guided Repulsion for Offline Reinforcement Learning — arXiv:2610.20190 — arXiv (en), https://arxiv.org/abs/2610.20190 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_336fcb1cdbf8 (Metraipolis archive dc_336fcb1cdbf8, sha256 c324dfc9f576074c7d7043cea870dda1c7200357fb24669160586a98cc422978)
BibTeX
@misc{dc336fcb1cdbf8,
title = {Value-Guided Repulsion for Offline Reinforcement Learning — arXiv:2610.20190},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20190},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_336fcb1cdbf8; sha256 c324dfc9f576074c7d7043cea870dda1c7200357fb24669160586a98cc422978},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20190. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Drifting models have emerged as a highly efficient and stable paradigm for policy design in offline reinforcement learning (RL). However, standard drift policies determine repulsion solely from geometric relationships among generated actions and therefore cannot distinguish them by expected value. To address this limitation, we introduce Value-Guided Repulsion Q-Learning (VRQL) to integrate action value estimates into the particle interaction field. For each state, VRQL combines geometric kernel distance with a normalized Q value scaling. This mechanism assigns greater repulsive influence to particles with lower values while strictly retaining attraction toward behavior action. Consequently, this value-guided interaction field aligns behavior regularization with policy improvement without adding an auxiliary behavior model stage. On 50 OGBench task configurations and 6 D4RL AntMaze configurations, VRQL demonstrates highly competitive performance against established baselines, suggesting that value-guided particle interaction is an effective method for offline RL. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.20190 — 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 2026-10-15T19:35:48.295Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).