Metraipolis › archive › dc_0aa8dae43d30

Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning — arXiv:2609.08080

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08080
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:06.550Z
SHA-256 of the archived text
3d748887383e83aa20a0a33f5b398e6cfa2d8c4b5585c9156ae88c70342a2ee5
Stable URL of this page
https://metraipolis.com/documento/dc_0aa8dae43d30

How to cite

Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning — arXiv:2609.08080 — arXiv (en), https://arxiv.org/abs/2609.08080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0aa8dae43d30 (Metraipolis archive dc_0aa8dae43d30, sha256 3d748887383e83aa20a0a33f5b398e6cfa2d8c4b5585c9156ae88c70342a2ee5)
BibTeX
@misc{dc0aa8dae43d30,
  title = {Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning — arXiv:2609.08080},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0aa8dae43d30; sha256 3d748887383e83aa20a0a33f5b398e6cfa2d8c4b5585c9156ae88c70342a2ee5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ensuring safety in reinforcement learning under nonstationarity requires anticipating changes in risk before they lead to unsafe behavior. Existing approaches typically rely on safety constraints defined at design time or updated reactively during execution, assuming that such constraints remain valid over time. However, in nonstationary environments with evolving contexts and changing driving layouts, these assumptions may fail. We propose a framework for proactive safety constraint generation based on context forecasting. The approach infers latent environmental context from observations, predicts its future evolution, and constructs safety constraints adapted to anticipated conditions. This enables the agent to proactively avoid unsafe regions instead of reacting only after safety violations occur. We evaluate the method in driving environments with structured context variation. The experiments include a sweep over nonstationarity intensities and additional held-out driving layouts, including highway, intersection, and racetrack scenarios. Results show that proactive constraint generation substantially reduces collisions under both seen and out-of-training nonstationarity intensities and generally remains effective across held-out driving layouts while maintaining usable task performance. These findings suggest that context-based constraint generation is a promising approach for safe reinforcement learning under nonstationarity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.08080 — 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 2026-10-16T13:39:43.018Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).