Metraipolis › archive › dc_130c03cacf8b
Equivalence Between Continuous-Time Risk-Sensitive Control and Rényi Divergence Minimization — arXiv:2609.07045
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07045
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T14:29:32.552Z
- SHA-256 of the archived text
50aef5aa34f1a0cee912fefad2d335d578aad22d8ec029186606babd91e14a92- Stable URL of this page
https://metraipolis.com/documento/dc_130c03cacf8b
How to cite
Equivalence Between Continuous-Time Risk-Sensitive Control and Rényi Divergence Minimization — arXiv:2609.07045 — arXiv (en), https://arxiv.org/abs/2609.07045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_130c03cacf8b (Metraipolis archive dc_130c03cacf8b, sha256 50aef5aa34f1a0cee912fefad2d335d578aad22d8ec029186606babd91e14a92)
BibTeX
@misc{dc130c03cacf8b,
title = {Equivalence Between Continuous-Time Risk-Sensitive Control and Rényi Divergence Minimization — arXiv:2609.07045},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07045},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_130c03cacf8b; sha256 50aef5aa34f1a0cee912fefad2d335d578aad22d8ec029186606babd91e14a92},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this study, we show that a continuous-time risk-sensitive control problem is equivalent to a Rényi divergence minimization problem over trajectory path measures. Reformulating stochastic optimal control as probabilistic inference via Kullback-Leibler (KL) divergence minimization avoids the computational intractability of the Hamilton-Jacobi-Bellman equation. However, standard KL control is inherently risk-neutral, and recent minimax extensions remain restricted to risk-averse settings. Our equivalence result resolves this limitation by offering a unified probabilistic framework for arbitrary risk attitudes in continuous-time nonlinear systems. Based on Girsanov theorem, we explicitly map the risk sensitivity to the Rényi divergence order, deriving a noise-dependent control penalty scaled by risk preference. This formulation seamlessly modulates tail-weighting behaviors, interpolating between zero-forcing for risk-averse policies and mass-covering for risk-seeking policies. These findings bridge stochastic control and information-theoretic inference, providing a foundation for sampling-based control algorithms. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-09 in math.OC). Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2609.07045 — 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 2026-10-16T14:09:21.680Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).