Metraipolis › archive › dc_0911ff082b80
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control — arXiv:2609.11014
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11014
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:26:46.629Z
- SHA-256 of the archived text
cacc3acf7b3a9d1529ae7b6428166b1d4669437062d4bb4d288fa68e2491efe3- Stable URL of this page
https://metraipolis.com/documento/dc_0911ff082b80
How to cite
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control — arXiv:2609.11014 — arXiv (en), https://arxiv.org/abs/2609.11014 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0911ff082b80 (Metraipolis archive dc_0911ff082b80, sha256 cacc3acf7b3a9d1529ae7b6428166b1d4669437062d4bb4d288fa68e2491efe3)
BibTeX
@misc{dc0911ff082b80,
title = {Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control — arXiv:2609.11014},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11014},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0911ff082b80; sha256 cacc3acf7b3a9d1529ae7b6428166b1d4669437062d4bb4d288fa68e2491efe3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11014. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon goal-conditioned reinforcement learning delegates control to a high-level module that proposes subgoals, but existing subgoals are implicit byproducts of value functions or latent actions, tied to the executor that produced them. We study a different object: a route-conditioned order of unavoidable stages that every successful executor must traverse, recoverable from offline trajectories and belonging to none of them. Its defining properties are topological: an unskippable stage is a separating set that every admissible path must cross, and a loop in free space forces a route choice. We read the two by homology in dimensions 0 and 1 over a transport-weighted carrier built from successful trajectories, yielding an enumerable gate set with shell-level certificates; the certified gates are what we call topological necessities. Certified gates enter the decision loop as a recursive topological gate hierarchy. Under a fixed, isomorphic free space, the object survives executor replacement: gates frozen on PointMaze data transfer without retraining to Ant and Humanoid, attaining the highest Humanoid aggregate under a unified interface (96.1), with +36.0 over a map-privileged reference on the multi-route task (p=1.4e-5); the planner saturates PointMaze (100+/-0) and matches or exceeds the strongest baselines on AntMaze (giant +22.9) and Kitchen (+15.8/+12.6). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.11014 — 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 2026-10-16T05:17:52.110Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).