Metraipolis › archive › dc_08d10d95af80

Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees — arXiv:2609.35874

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35874
License (as archived)
CC0-1.0
Archived
2026-10-07T16:22:07.744Z
SHA-256 of the archived text
5f8bcbf2e99bf16785a04eccb3db4cf14799f6d0a942ebd908a8cbbd55fc9fbe
Stable URL of this page
https://metraipolis.com/documento/dc_08d10d95af80

How to cite

Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees — arXiv:2609.35874 — arXiv (en), https://arxiv.org/abs/2609.35874 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08d10d95af80 (Metraipolis archive dc_08d10d95af80, sha256 5f8bcbf2e99bf16785a04eccb3db4cf14799f6d0a942ebd908a8cbbd55fc9fbe)
BibTeX
@misc{dc08d10d95af80,
  title = {Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees — arXiv:2609.35874},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35874},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08d10d95af80; sha256 5f8bcbf2e99bf16785a04eccb3db4cf14799f6d0a942ebd908a8cbbd55fc9fbe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35874. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Online POMDP planners optimize the expected cumulative cost, which can mask dangerous states when the belief places significant mass on high-cost states. Existing risk-averse methods apply static or dynamic Conditional Value at Risk (CVaR) to the value function, capturing trajectory-level risk, but share two gaps: (i) by retaining the immediate cost as an expectation of a state-dependent cost over the belief, the risk \emph{within} the belief is left unaddressed; and (ii) by modifying the value function, they require new tailored algorithms rather than reusing existing expectation-based planners. We instead apply CVaR to the immediate cost over the belief at each step, directly targeting per-step uncertainty about the current state. The standard expected cumulative return is retained as the objective, so the resulting problem has a standard MDP structure: any expectation-based POMDP planner can be made risk-sensitive by changing only the cost computation. We inherit finite-time guarantees for policy evaluation and sparse sampling---with estimation error independent of the risk level---and, as our central theoretical result, prove a finite-time bound on the gap between the particle belief MDP surrogate and the original POMDP, which together yield an end-to-end guarantee from the true POMDP value to the algorithmic estimate. In the risk-neutral limit, the formulation recovers standard expectation-based planning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35874 — 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 2026-10-07T15:54:53.441Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).