pith:CLKGG7GH
Constrained Policy Optimization with Cantelli-Bounded Value-at-Risk
VaR-CPO approximates Value-at-Risk constraints via Cantelli's inequality to guarantee zero violations during training in feasible reinforcement learning environments.
arxiv:2601.22993 v4 · 2026-01-30 · cs.LG · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CLKGG7GH3AZD7NMO22XQLBJ7OR}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
VaR-CPO achieves zero constraint violations during training in feasible environments, a property baseline methods fail to uphold, while providing worst-case bounds for policy improvement and constraint violation.
The Cantelli inequality provides a sufficiently tight and conservative approximation to the true VaR constraint so that enforcing the bound still guarantees the original probabilistic constraint in practice.
VaR-CPO approximates non-differentiable VaR constraints via Cantelli's inequality to enable safe, sample-efficient policy optimization with zero training violations in feasible environments.
Formal links
Receipt and verification
| First computed | 2026-06-30T01:17:33.333863Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
12d4637cc7d8323fb58ed6af05853f747e55a2b67d4353530956dd25adbf10a5
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CLKGG7GH3AZD7NMO22XQLBJ7OR \
| 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: 12d4637cc7d8323fb58ed6af05853f747e55a2b67d4353530956dd25adbf10a5
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a662487e501e5952911af607c6e10b4bdbd3b18692871938a12ba80531e99d48",
"cross_cats_sorted": [
"stat.ML"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-01-30T13:57:47Z",
"title_canon_sha256": "30ce4acde7984652dff459c97f283d90840781c4c1a41d0540b94b58f3c4c83c"
},
"schema_version": "1.0",
"source": {
"id": "2601.22993",
"kind": "arxiv",
"version": 4
}
}