Metraipolis › archive › dc_1379e810b138

Planned Restlessness: Delayed Meta Bandits with Budgets — arXiv:2610.38955

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38955
License (as archived)
CC0-1.0
Archived
2026-11-01T02:24:56.381Z
SHA-256 of the archived text
4b9ae51b8fa50816d9451dfcce94d8a61a7d7fdd610cc93b27dc5d860b98d584
Stable URL of this page
https://metraipolis.com/documento/dc_1379e810b138

How to cite

Planned Restlessness: Delayed Meta Bandits with Budgets — arXiv:2610.38955 — arXiv (en), https://arxiv.org/abs/2610.38955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1379e810b138 (Metraipolis archive dc_1379e810b138, sha256 4b9ae51b8fa50816d9451dfcce94d8a61a7d7fdd610cc93b27dc5d860b98d584)
BibTeX
@misc{dc1379e810b138,
  title = {Planned Restlessness: Delayed Meta Bandits with Budgets — arXiv:2610.38955},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38955},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1379e810b138; sha256 4b9ae51b8fa50816d9451dfcce94d8a61a7d7fdd610cc93b27dc5d860b98d584},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study episodic finite-horizon Bayesian bandits, or meta-bandits, with independent arms. Each episode draws fresh arm qualities from unknown recurring priors. Observations arrive after known delays, and plays obey hard per-episode caps and total budgets. A play earns reward and informs both the current quality and the recurring prior: the learner must explore, use, and generalize. We formulate a common planning optimization over learning trajectories. Its LP relaxation values experiments through current reward, resource consumption and continuation: the value of future decisions from the learning state produced. Dual prices separate the arms into local programs and certify every admissible policy, including hierarchical Thompson sampling. Execution enforces the hard constraints while preserving the promised learning transitions or accounting for their loss. The framework also represents risk-sensitive objectives and prices purchased observations and buyout options. Delayed reports create planned restlessness: an arm's information changes while it is not played, through reports of its own earlier plays arriving on a known calendar. For stationary priors, finite reward alphabets, bounded report lag and nonbinding budgets, posterior sampling over the recurring priors bounds the price of not knowing them by $O(\sqrt{N})$ over $N$ episodes, with other parameters fixed. For one undelayed $T$-step episode with arms capped at $T/X$ plays each, we obtain the LP-relative approximation factor $1+(2\pi X)^{-1/2}+O(X^{-1})$, improving previous factors, with a matching lower bound for the leading term.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Data Structures and Algorithms (cs.DS).
Pagina del lavoro: https://arxiv.org/abs/2610.38955 — 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 2026-11-01T02:12:44.141Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).