Metraipolis › archive › dc_7e07d00fa356

Safe Meta-Reinforcement Learning via Information Space Reachability — arXiv:2609.15915

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15915
License (as archived): CC0-1.0
Archived: 2026-10-16T00:12:10.680Z
SHA-256 of the archived text: c52a71a10dda87efb54e64aa8ae6dc0c3132808d02f50214c8c145af1a4a0ccd
Stable URL of this page: https://metraipolis.com/documento/dc_7e07d00fa356

How to cite

Safe Meta-Reinforcement Learning via Information Space Reachability — arXiv:2609.15915 — arXiv (en), https://arxiv.org/abs/2609.15915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e07d00fa356 (Metraipolis archive dc_7e07d00fa356, sha256 c52a71a10dda87efb54e64aa8ae6dc0c3132808d02f50214c8c145af1a4a0ccd)

BibTeX

@misc{dc7e07d00fa356,
  title = {Safe Meta-Reinforcement Learning via Information Space Reachability — arXiv:2609.15915},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15915},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e07d00fa356; sha256 c52a71a10dda87efb54e64aa8ae6dc0c3132808d02f50214c8c145af1a4a0ccd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL in real-world tasks is hindered by safety requirements, which have been underexplored in prior work. In this paper, we propose a safe meta-RL framework that explicitly accounts for safety during adaptation. Our key insight is to reason about safety in the information space, which captures both the physical state and the agent's belief over the underlying task. Within this space, we introduce a safety value function that measures the probability of the agent avoiding unsafe regions indefinitely. We show that this function satisfies a self-consistency condition and a Bellman equation, which make it learnable via meta-RL. Based on this formulation, we develop a safe meta-RL algorithm that learns the safety value function and leverages it for safety filtering and constrained policy optimization. Experiments on meta-RL benchmarks demonstrate the effectiveness of the proposed method.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.15915 — 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 2026-10-15T23:54:14.801Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).