Metraipolis › archive › dc_518ecbe084e6

Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model — arXiv:2610.06931

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06931
License (as archived)
CC0-1.0
Archived
2026-10-07T11:40:38.485Z
SHA-256 of the archived text
357c11c2d2cee033aae7537250d5cdee07152150ddc4653fcb3a3b1ee779b58a
Stable URL of this page
https://metraipolis.com/documento/dc_518ecbe084e6

How to cite

Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model — arXiv:2610.06931 — arXiv (en), https://arxiv.org/abs/2610.06931 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_518ecbe084e6 (Metraipolis archive dc_518ecbe084e6, sha256 357c11c2d2cee033aae7537250d5cdee07152150ddc4653fcb3a3b1ee779b58a)
BibTeX
@misc{dc518ecbe084e6,
  title = {Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model — arXiv:2610.06931},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06931},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_518ecbe084e6; sha256 357c11c2d2cee033aae7537250d5cdee07152150ddc4653fcb3a3b1ee779b58a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06931. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we study the sample complexities of value and policy learning in finite discounted Markov decision processes (MDPs) under recursive entropic risk preferences with risk parameter \(\beta\neq 0\), assuming access to a generative model of the MDP. We provide a refined analysis of model-based risk-sensitive Q-value iteration (MB-RS-QVI), a plug-in model-based method introduced in prior work, and derive \((\varepsilon,\delta)\)-PAC guarantees for both learning the optimal \(Q\)-value function and an \(\varepsilon\)-optimal policy. Our bounds improve the exponential dependence on the effective horizon \(1/(1-\gamma)\) compared with the best existing guarantees for this setting. In particular, they match the existing lower bounds in their exponential dependence on \(|\beta|/(1-\gamma)\), as well as in \(S\), \(A\), \(\varepsilon\), and \(|\beta|\), up to logarithmic factors. Consequently, our analysis removes the exponential gap between the previously known upper and lower bounds, leaving only a polynomial gap in the effective horizon.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.06931 — 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 2026-10-07T11:19:24.707Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).