Metraipolis › archive › dc_812e9c56567d

Amortized Feedback Planning: Turning Model-Based Rollouts into Executable Policies — arXiv:2609.35012

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35012
License (as archived)
CC0-1.0
Archived
2026-10-07T23:06:45.452Z
SHA-256 of the archived text
0bf8bd80d852c2b80e7ce9c0e05c40f0ce1a322ca9ac3b187f5836e4d9bf1c5b
Stable URL of this page
https://metraipolis.com/documento/dc_812e9c56567d

How to cite

Amortized Feedback Planning: Turning Model-Based Rollouts into Executable Policies — arXiv:2609.35012 — arXiv (en), https://arxiv.org/abs/2609.35012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_812e9c56567d (Metraipolis archive dc_812e9c56567d, sha256 0bf8bd80d852c2b80e7ce9c0e05c40f0ce1a322ca9ac3b187f5836e4d9bf1c5b)
BibTeX
@misc{dc812e9c56567d,
  title = {Amortized Feedback Planning: Turning Model-Based Rollouts into Executable Policies — arXiv:2609.35012},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35012},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_812e9c56567d; sha256 0bf8bd80d852c2b80e7ce9c0e05c40f0ce1a322ca9ac3b187f5836e4d9bf1c5b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Closed-loop planning accounts for future observation-dependent actions but can be expensive to repeat at deployment. Bellman-gradient (BG) refinement differentiates conditional rollouts through an existing actor, corrects the current action, and stores the result in an executable policy. A backward sweep reuses deployed future feedback; full-horizon rollouts in an identified Gaussian belief model need no learned value critic. A nonlinear error recursion links quadratic continuation error, local correction, and policy storage. A controlled non-LQG example exhibits second-order policy accuracy with consistent storage, while ideal affine LQG admits exact backward recovery. In nonquadratic thrust, BG reduces actor cost by 2.47-3.20% and remains within 0.13-0.53% of the tested feedback MPC; original policies execute in 5-6 microseconds in a seed-0 native audit. With matched storage, BG attains competitive plant costs at about one ninth (arm) and one sixtieth (docking) of feedback-teacher-plus-student construction time on one GPU, excluding shared learning and node preparation. Richer common maps substantially narrow some student-BG gaps. These results expose the roles of learned feedback, local correction, and storage in executable control.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.OC).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.35012 — 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 2026-10-07T22:42:39.265Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).