pith:AKT4PA27
Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning
Reach-avoid probability certificates turn stochastic safety constraints into a surrogate objective that reinforcement learners can optimize for minimum cost.
arxiv:2605.11975 v2 · 2026-05-12 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{AKT4PA27VFE5BJD7YPCZ75ZTEF}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We establish almost sure convergence of the proposed algorithms to locally optimal policies with respect to the resulting objective.
That reach-avoid probability certificates can be computed or approximated accurately enough during learning to serve as a reliable surrogate for the true probabilistic constraint in stochastic environments.
Introduces RAPCs and a contraction Bellman operator that jointly enforce probabilistic reach-avoid constraints while minimizing expected costs in stochastic RL, with almost-sure convergence to local optima.
Formal links
Receipt and verification
| First computed | 2026-05-20T00:04:36.370095Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
02a7c7835fa949d0a47fc3c59ff73321548bc7f5ee6ec7f71478e8fe76a26526
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/AKT4PA27VFE5BJD7YPCZ75ZTEF \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 02a7c7835fa949d0a47fc3c59ff73321548bc7f5ee6ec7f71478e8fe76a26526
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "0a8a6fcc79b1dafa5a3fd8818da64a1986023d846c8114d99a5698cd87cbac34",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-12T11:31:36Z",
"title_canon_sha256": "66d720cff133972aa7823b5ebaac80077487d3c568a5519b8ddfdb598a6eb03a"
},
"schema_version": "1.0",
"source": {
"id": "2605.11975",
"kind": "arxiv",
"version": 2
}
}