Newest papers

Deep Pontryagin Learning for Continuous-Time Stochastic Control with Jumps

Jean-Loup Dupret, Patrick Cheridito · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26718 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Desenvolvemos um quadro de aprendizagem Pontryagin profundo para problemas de controle estocástico de tempo contínuo de alta dimensão que acomoda naturalmente saltos-difusões. Em contraste com a otimização de políticas diretas, que diferencia repetidamente o objetivo através de toda a dinâmica discretizada no tempo, nosso método separa o aprendizado adjunto da melhoria de políticas, incorporando explicitamente informações de estado-sensibilidade do princípio estocástico de Pontryagin. Para um controlo de Markov fixo, nós computamos primeiro rótulos adjuntos por caminho, retropropagando a recompensa ao longo do tempo ao longo de trajetórias de estado simuladas, e projetamos esses rótulos para o estado de Markov através de um passo de regressão supervisionado. O controle é então atualizado através da aplicação da condição de

Machine translation (Meta M2M100); the English original follows.

Abstract

We develop a deep Pontryagin learning framework for high-dimensional continuous-time stochastic control problems that naturally accommodates jump-diffusions. In contrast to direct policy optimization, which repeatedly differentiates the objective through the entire time-discretized dynamics, our method separates adjoint learning from policy improvement by explicitly incorporating state-sensitivity information from the Pontryagin stochastic maximum principle. For a fixed Markov control, we first compute pathwise adjoint labels by backpropagating the reward through time along simulated state trajectories, and project these labels onto the Markov state through a supervised regression step. The control is then updated by enforcing the pointwise Hamiltonian stationarity condition. We prove that the resulting projected adjoint process satisfies a discrete-time Pontryagin principle and converges, as the time step tends to zero, to the solution of the corresponding continuous-time adjoint backward stochastic differential equation. Numerical experiments illustrate the accuracy, stability, and scalability of the approach.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Pointwise, Mathematics, Optimal control, Pontryagin's minimum principle, Markov chain, Markov process

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26718, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange