Metraipolis › archive › dc_67bf6d7ea0f7
RL-PaO: Prediction as Action in Decision Making under Uncertainty — arXiv:2609.37065
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37065
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:30:21.050Z
- SHA-256 of the archived text
ed16137270085837361d5617ba6730314c068f3e52ddb0139f46ae3ea0d97300- Stable URL of this page
https://metraipolis.com/documento/dc_67bf6d7ea0f7
How to cite
RL-PaO: Prediction as Action in Decision Making under Uncertainty — arXiv:2609.37065 — arXiv (en), https://arxiv.org/abs/2609.37065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_67bf6d7ea0f7 (Metraipolis archive dc_67bf6d7ea0f7, sha256 ed16137270085837361d5617ba6730314c068f3e52ddb0139f46ae3ea0d97300)
BibTeX
@misc{dc67bf6d7ea0f7,
title = {RL-PaO: Prediction as Action in Decision Making under Uncertainty — arXiv:2609.37065},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37065},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_67bf6d7ea0f7; sha256 ed16137270085837361d5617ba6730314c068f3e52ddb0139f46ae3ea0d97300},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decision-making under uncertainty often relies on predicted parameters, yet accurate prediction does not necessarily lead to good operational decisions. Aligning prediction with downstream optimization requires learning from the consequences of the decisions those predictions induce. We introduce RL-PaO, a reinforcement learning framework that integrates system formulation, optimization, and decision execution into a single environment. This yields a Markov decision process in which prediction is regarded as action: it shifts the environment to produce subsequent context and reward that explicitly aligns prediction error with realized cost, and learning the optimal policy does not require differentiating through the black-box solver. We evaluate RL-PaO on day-ahead energy scheduling using real historical data. On the test year, RL-PaO achieves the lowest annual cost among the non-oracle baselines, achieving on average $10\%$ cost reduction. Moreover, RL-PaO is capable of further analyses to provide strong interpretability both from the policy evolution perspective and the cost-accuracy trade-off. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.37065 — 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 2026-10-07T16:59:48.282Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).