Metraipolis › archive › dc_3346f147f787
FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems — arXiv:2610.12432
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12432
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:26:22.392Z
- SHA-256 of the archived text
247571011377d7666a2779aea55be84ada98528b58a099b1fbf5f6bfbde8ad71- Stable URL of this page
https://metraipolis.com/documento/dc_3346f147f787
How to cite
FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems — arXiv:2610.12432 — arXiv (en), https://arxiv.org/abs/2610.12432 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3346f147f787 (Metraipolis archive dc_3346f147f787, sha256 247571011377d7666a2779aea55be84ada98528b58a099b1fbf5f6bfbde8ad71)
BibTeX
@misc{dc3346f147f787,
title = {FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems — arXiv:2610.12432},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12432},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3346f147f787; sha256 247571011377d7666a2779aea55be84ada98528b58a099b1fbf5f6bfbde8ad71},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12432. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Safe reinforcement learning commonly places safety and task performance in the same policy objective, where they can introduce competing updates. Safety filters separate them at action execution, but classical designs require an analytic safety function and dynamics model, and standard minimal-intervention filters are myopic to long-horizon task return because they minimize only instantaneous action deviation. Hard projections are also undefined when no safe action exists. We present FAITH, a feasibility-aware, model-free framework that approximates the optimal state-action safety value and amortizes minimal-intervention filtering with a feedforward network. The task policy optimizes the task return through the filtered dynamics, which recovers the feasible constrained problem without a competing safety term in the task-policy update. When no action satisfies the learned safety condition, the same filter approaches the action with minimum predicted peak harm. On a double integrator example and a Safety Gym environment, FAITH achieves the highest return among methods with no feasible-start violations and matches the lowest harm from infeasible starts. On a 29-DoF humanoid, it reaches a 99.95% safety rate while retaining 97% of the unfiltered return in Walking-Avoid, and obtains the highest measured safety rate in Push-Avoid by learning to sacrifice balancing and fall away from the protected region. The same policies are also demonstrated on a real-world Unitree G1 humanoid. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.12432 — 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 2026-10-09T05:50:32.302Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).