Metraipolis › archive › dc_4afbe576d22d

Hyperbolic Inverse Reinforcement Learning — arXiv:2610.42104

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42104
License (as archived)
CC0-1.0
Archived
2026-11-03T05:41:14.607Z
SHA-256 of the archived text
557210be4f5d763e09498a2759558241efb0076995dd7323df218ae41ade4db9
Stable URL of this page
https://metraipolis.com/documento/dc_4afbe576d22d

How to cite

Hyperbolic Inverse Reinforcement Learning — arXiv:2610.42104 — arXiv (en), https://arxiv.org/abs/2610.42104 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4afbe576d22d (Metraipolis archive dc_4afbe576d22d, sha256 557210be4f5d763e09498a2759558241efb0076995dd7323df218ae41ade4db9)
BibTeX
@misc{dc4afbe576d22d,
  title = {Hyperbolic Inverse Reinforcement Learning — arXiv:2610.42104},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42104},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4afbe576d22d; sha256 557210be4f5d763e09498a2759558241efb0076995dd7323df218ae41ade4db9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42104. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Inverse reinforcement learning (IRL) seeks to infer the reward function underlying observed behavior, but its predictive accuracy and interpretability depend on how that reward is computed from the underlying features. While prior IRL reward functions have been implemented through a variety of techniques including linear weights, neural networks, or other function approximators, none make assumptions about the geometry of the underlying feature space. Inspired by geometric organization observed in neural circuits, we introduce Hyperbolic inverse reinforcement learning (Hyperbolic IRL), which parameterizes reward as a function of Hyperbolic distance between the feature vector and a learned parameter vector, as well as its Euclidean distance variant. We tested our methods against a range of linear and nonlinear IRL baselines under both deterministic and stochastic policies. Our Hyperbolic approach achieved comparable performance to state-of-the-art models on established benchmarks and excelled in the low data limit and across dense environments. Applied to human navigation among multiple exhibits in a museum room, Hyperbolic IRL reveals reward structure that depends not only on individual exhibit-distance features, but also on non-separable conjunctions between them. Together, these results demonstrate that a Hyperbolic reward parameterization can improve both the predictive accuracy and interpretability of IRL, providing a framework for studying how non-separable, conjunctive structure can begin to explain behavior.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.42104 — 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 2026-11-03T05:26:25.795Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).