Metraipolis › archive › dc_db8071fc532e

Can Jev be Your Q or Policy in Reinforcement Learning? — arXiv:2610.11692

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11692
License (as archived)
CC0-1.0
Archived
2026-10-09T06:00:34.557Z
SHA-256 of the archived text
89da3c97eb83b9bd839346d2365861a35a1c10fb80cfbb4c4d0ef992d81a7f8d
Stable URL of this page
https://metraipolis.com/documento/dc_db8071fc532e

How to cite

Can Jev be Your Q or Policy in Reinforcement Learning? — arXiv:2610.11692 — arXiv (en), https://arxiv.org/abs/2610.11692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db8071fc532e (Metraipolis archive dc_db8071fc532e, sha256 89da3c97eb83b9bd839346d2365861a35a1c10fb80cfbb4c4d0ef992d81a7f8d)
BibTeX
@misc{dcdb8071fc532e,
  title = {Can Jev be Your Q or Policy in Reinforcement Learning? — arXiv:2610.11692},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11692},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db8071fc532e; sha256 89da3c97eb83b9bd839346d2365861a35a1c10fb80cfbb4c4d0ef992d81a7f8d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation models supply reinforcement learning (RL) with priors that mitigate its longstanding weaknesses in sample efficiency and transfer, but their token-by-token generation makes queries sequential and costly. Jev, a recently released decision model, generates nothing and returns calibrated, typed answers in a single forward pass. Existing work studies foundation models in RL either as models to be trained or as generators to be prompted, and Jev belongs to neither category, having so far served only as a black box in single domains. How well such a model decides on its own in RL environments, and how it can improve RL as a component of training, therefore remain unaddressed. To this end, in this paper we first examine the requirements that the objects of an RL system place on the answers they consume, and establish that Jev can fulfill all of them except the cardinal use of a value function. The remaining objects form positions that admit several roles each. We then construct algorithms that employ Jev at three of these positions, as a reference policy, an exploration judge, and a replay rater, to improve sample efficiency, exploration, and learning performance. Across nine MiniGrid tasks and three Atari games, training with Jev outperforms a standard RL learner, including where the learner makes no progress alone, while the model itself remains untrained. To our knowledge, we present the first use of Jev within the RL learning process and establish a frozen decision model as a usable component of RL training, inviting further exploration of how Jev and other advanced decision models can improve RL.

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/2610.11692 — 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 2026-10-09T05:47:01.885Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).