Metraipolis › archive › dc_dd077fc33cb4

Sample-Efficiency of Kolmogorov-Arnold Networks — arXiv:2610.10627

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10627
License (as archived)
CC0-1.0
Archived
2026-10-09T06:20:51.671Z
SHA-256 of the archived text
9fad7fd6e27adfc2583e9c4d2e0772e7d754f441a47957afa694a2df44c4575d
Stable URL of this page
https://metraipolis.com/documento/dc_dd077fc33cb4

How to cite

Sample-Efficiency of Kolmogorov-Arnold Networks — arXiv:2610.10627 — arXiv (en), https://arxiv.org/abs/2610.10627 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd077fc33cb4 (Metraipolis archive dc_dd077fc33cb4, sha256 9fad7fd6e27adfc2583e9c4d2e0772e7d754f441a47957afa694a2df44c4575d)
BibTeX
@misc{dcdd077fc33cb4,
  title = {Sample-Efficiency of Kolmogorov-Arnold Networks — arXiv:2610.10627},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10627},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd077fc33cb4; sha256 9fad7fd6e27adfc2583e9c4d2e0772e7d754f441a47957afa694a2df44c4575d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10627. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep reinforcement learning has achieved substantial performance gains over classical control approaches. Yet, a central challenge to learning in real-world applications is acquiring costly samples. Kolmogorov-Arnold Networks are a recently proposed architecture that can learn physical relationships in control problems effectively, with significantly higher parameter efficiency and interpretability when compared to Multi-Layer-Perceptron architectures. In this work, we systematically study sample-efficiency using computational experiments, covering the Feynman dataset and the Gymnasium RL benchmark. The results show that similar performance can be achieved with 40% fewer samples using the Kolmogorov-Arnold architecture, and that relative performance improvements up to 50% occur during the training process. The observed gains are robust to varying levels of noise in rewards. These results highlight the potential of the Kolmogorov-Arnold architectures for more sample-efficient reinforcement learning. Code: this https URL

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/2610.10627 — 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 2026-10-09T05:50:30.889Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).