Metraipolis › archive › dc_0a0416623477

Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching — arXiv:2609.38955

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38955
License (as archived)
CC0-1.0
Archived
2026-10-07T12:44:38.876Z
SHA-256 of the archived text
b379088e00c5ae17f068da54f4f9b33bc92c7e165ac22f0650a2fe2dabb623b5
Stable URL of this page
https://metraipolis.com/documento/dc_0a0416623477

How to cite

Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching — arXiv:2609.38955 — arXiv (en), https://arxiv.org/abs/2609.38955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0a0416623477 (Metraipolis archive dc_0a0416623477, sha256 b379088e00c5ae17f068da54f4f9b33bc92c7e165ac22f0650a2fe2dabb623b5)
BibTeX
@misc{dc0a0416623477,
  title = {Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching — arXiv:2609.38955},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38955},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0a0416623477; sha256 b379088e00c5ae17f068da54f4f9b33bc92c7e165ac22f0650a2fe2dabb623b5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Inverse Reinforcement Learning (IRL) aims to recover a reward function that explains expert demonstrations. Existing IRL methods typically rely on a bi-level optimization procedure that alternates between reward learning and policy optimization, leading to substantial computational burden and training instability. In this work, we introduce a different route that eliminates policy optimization entirely by leveraging diffusion policies. Our key insight is that a diffusion policy encodes the action-gradient structure of the optimal soft Q function, enabling reward learning to be cast as a sequence of value recovery problems, thereby allowing us to bypass reward-policy loops inherent in prior IRL methods. Specifically, our method proceeds in three stages: (I) recovering the optimal soft Q function via action-gradient matching and estimating the corresponding soft value function (LogSumExp of Q values) in a way inspired by Gumbel regression; (II) calibrating these soft values by inferring a state-dependent offset; (III) extracting the reward by enforcing Bellman consistency. This leads to Loop-Free Inverse Reinforcement Learning (LFIRL), a fully offline algorithm that operates in a simple, loop-free, and sequential manner. LFIRL is simple to implement and significantly improves training efficiency while maintaining strong reward recovery performance. Empirically, across Maze, Franka Kitchen, Adroit Hand Pen, and Push-T benchmarks, LFIRL achieves 2-3x speedup over the fastest baselines, while matching or surpassing state-of-the-art methods in reward recovery quality.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38955 — 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 2026-10-07T12:14:13.984Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).