Metraipolis › archive › dc_90e880fbcc82
Geometric Distributional Control: Learning Progress with Partial Structural Knowledge — arXiv:2609.06331
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06331
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:30:51.570Z
- SHA-256 of the archived text
48381f1d4d6c081b4290e9031f4ff391febe21dfec29eb06f96191d778958018- Stable URL of this page
https://metraipolis.com/documento/dc_90e880fbcc82
How to cite
Geometric Distributional Control: Learning Progress with Partial Structural Knowledge — arXiv:2609.06331 — arXiv (en), https://arxiv.org/abs/2609.06331 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90e880fbcc82 (Metraipolis archive dc_90e880fbcc82, sha256 48381f1d4d6c081b4290e9031f4ff391febe21dfec29eb06f96191d778958018)
BibTeX
@misc{dc90e880fbcc82,
title = {Geometric Distributional Control: Learning Progress with Partial Structural Knowledge — arXiv:2609.06331},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06331},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90e880fbcc82; sha256 48381f1d4d6c081b4290e9031f4ff391febe21dfec29eb06f96191d778958018},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06331. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-time control often sits between two limiting regimes. Predictive optimization and model-based control are powerful when dynamics, parameters, objectives, and online planning models are specified; reinforcement learning can relax this requirement, but must infer long-horizon value signals from sequential data and interaction, making training slow, high-variance, and hard to scale in large action spaces. This middle regime is common in systems including autonomous driving, warehouse robotics, traffic control, and delivery drones: partial geometry, physics, rules, or constraints are known, yet the local direction of task progress remains uncertain. Geometric Distributional Control (GDC) is designed for this partial-knowledge setting. It factorizes control into feasibility and progress: known geometry, rules, constraints, and response maps define an executable scaffold, while progress-weighted feasible data learns the missing directional signal on that scaffold. The learned score acts as a Bellman-like local value-gradient, selecting actions that make progress without requiring global Bellman recursion, a fully specified planner, or a black-box policy that absorbs both feasibility and preference. This knowledge can be lightweight and partial, such as simple dynamics, safety filters, local maps, constraint projectors, or lower-level response maps; it need not encode full dynamics or a long-horizon objective. Offline, GDC fits a progress-tilted distribution from short known-feasible snippets with weak signed progress certificates. Online, its score is projected through the scaffold and applied in receding-horizon feedback. We prove that this score descends a data-induced soft progress value and validate GDC on structured multilevel optimization and SUMO route-progress driving, where it improves over known-only solvers and learning baselines while preserving scaffold-enforced feasibility. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO). Categorie arXiv: Robotics (cs.RO) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2609.06331 — 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 2026-10-16T15:11:47.528Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).