Metraipolis › archive › dc_d27bca44b237
Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field Control — arXiv:2610.11619
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11619
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:24:09.231Z
- SHA-256 of the archived text
9e67c383ea14d5244dd8529f41082dd0b8ff2784698bf82525c3104584a443cf- Stable URL of this page
https://metraipolis.com/documento/dc_d27bca44b237
How to cite
Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field Control — arXiv:2610.11619 — arXiv (en), https://arxiv.org/abs/2610.11619 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d27bca44b237 (Metraipolis archive dc_d27bca44b237, sha256 9e67c383ea14d5244dd8529f41082dd0b8ff2784698bf82525c3104584a443cf)
BibTeX
@misc{dcd27bca44b237,
title = {Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field Control — arXiv:2610.11619},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11619},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d27bca44b237; sha256 9e67c383ea14d5244dd8529f41082dd0b8ff2784698bf82525c3104584a443cf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11619. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop a model-free policy gradient method for discrete-time mean-field control (MFC). In MFC, the policy affects the objective both through the controlled dynamics and through the population distribution. Standard REINFORCE estimators capture the first effect but not the second. We introduce Transport REINFORCE, a transport map-based approach that perturbs a suitable transformation of the population distribution to estimate this missing mean-field contribution. The method applies to both finite and continuous state spaces. In finite state spaces, we perturb the population distribution directly on the probability simplex through a convex combination of the current population weights and random weights. In continuous state spaces, we project the population distribution onto the manifold of Gaussian mixtures, and then randomize it via a transport map that ensures the perturbed law remains within this manifold. We prove consistency of the perturbed objective and gradient as the perturbation vanishes, and derive bias and mean-square error bounds for the resulting sample-based gradient estimator. Numerical experiments on several MFC benchmarks show that Transport REINFORCE improves over standard REINFORCE. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.11619 — 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 2026-10-09T05:50:32.100Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).