Metraipolis › archive › dc_8bbd9666b0ec

Scale-free adaptive planning for deterministic dynamics & discounted rewards — arXiv:2604.18312

Source
arXiv (en)
Original
https://arxiv.org/abs/2604.18312
License (as archived)
CC0-1.0
Archived
2026-10-06T09:32:57.063Z
SHA-256 of the archived text
a03d955d55e85937006950dfb47effbb1bc63ca905cd4b2e5a2ef936363b9f96
Stable URL of this page
https://metraipolis.com/documento/dc_8bbd9666b0ec

How to cite

Scale-free adaptive planning for deterministic dynamics & discounted rewards — arXiv:2604.18312 — arXiv (en), https://arxiv.org/abs/2604.18312 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bbd9666b0ec (Metraipolis archive dc_8bbd9666b0ec, sha256 a03d955d55e85937006950dfb47effbb1bc63ca905cd4b2e5a2ef936363b9f96)
BibTeX
@misc{dc8bbd9666b0ec,
  title = {Scale-free adaptive planning for deterministic dynamics & discounted rewards — arXiv:2604.18312},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2604.18312},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bbd9666b0ec; sha256 a03d955d55e85937006950dfb47effbb1bc63ca905cd4b2e5a2ef936363b9f96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2604.18312. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value function is not known, nor are the rewards bounded. We propose Platypoos, a simple scale-free planning algorithm that adapts to the unknown scale and smoothness of the reward function. We provide a sample complexity analysis for Platypoos that improves upon prior work and holds simultaneously over a broad range of discount factors and reward scales, without the algorithm knowing them. We also establish a matching lower bound showing our analysis is optimal up to constants.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2604.18312 — 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 2026-10-06T08:24:13.962Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).