Metraipolis › archive › dc_911bf5eb7b29

Average-Reward Policy Identification from a Single Continuing Trajectory — arXiv:2610.20486

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20486
License (as archived)
CC0-1.0
Archived
2026-10-15T14:20:37.314Z
SHA-256 of the archived text
52802d43c91aa5b884dbd293ad2e5bc5b16e3f3d2fdf85ed915d25589fdf7906
Stable URL of this page
https://metraipolis.com/documento/dc_911bf5eb7b29

How to cite

Average-Reward Policy Identification from a Single Continuing Trajectory — arXiv:2610.20486 — arXiv (en), https://arxiv.org/abs/2610.20486 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_911bf5eb7b29 (Metraipolis archive dc_911bf5eb7b29, sha256 52802d43c91aa5b884dbd293ad2e5bc5b16e3f3d2fdf85ed915d25589fdf7906)
BibTeX
@misc{dc911bf5eb7b29,
  title = {Average-Reward Policy Identification from a Single Continuing Trajectory — arXiv:2610.20486},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20486},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_911bf5eb7b29; sha256 52802d43c91aa5b884dbd293ad2e5bc5b16e3f3d2fdf85ed915d25589fdf7906},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20486. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions. Unlike methods that can freely sample any state--action pair, an agent learning from a single trajectory must spend additional time navigating between states. It is therefore natural to expect that learning from a single trajectory requires more experience. In this paper, we show that this additional cost is not always necessary. For average-reward reinforcement learning, we develop an algorithm that learns where to collect information while ensuring that the required samples can be obtained efficiently. We establish an upper bound on the number of interactions needed to identify a near-optimal policy. Furthermore, we prove a matching information theoretic lower bound, showing that, for a broad class of environments and at sufficiently high accuracy, learning from a single trajectory is no harder in the worst case than learning with unrestricted access to state action samples. Our results reveal that the additional complexity cost of navigation can be avoided by adapting information gathering requirements to how the environment provides information.

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/2610.20486 — 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 2026-10-15T13:53:35.762Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).