pith:AZNIU77B
Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
The Partition Multilinear Extension supplies unbiased marginal gradients from submodular difference rewards for decentralized categorical policies.
arxiv:2605.13269 v1 · 2026-05-13 · eess.SY · cs.SY
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{AZNIU77BOJ4W2ZROBHQD3MQZIL}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We prove a stagewise 1/2-approximation guarantee and sublinear dynamic regret in slowly varying environments, measured by the path length of the optimal PME marginals.
The team utility function is submodular, which is required for submodular difference rewards to supply unbiased PME marginal-gradient information.
SubMAPG uses a new Partition Multilinear Extension to derive unbiased policy gradients from submodular difference rewards, delivering 1/2-approximation and sublinear dynamic regret for online distributed task allocation in open multi-agent systems.
References
Receipt and verification
| First computed | 2026-05-18T02:44:49.291442Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
065a8a7fe172796d662e09e03db21942f08a82e958204274b2a0c48e44e6f2f6
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/AZNIU77BOJ4W2ZROBHQD3MQZIL \
| 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: 065a8a7fe172796d662e09e03db21942f08a82e958204274b2a0c48e44e6f2f6
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "83fb0d56f5a4eba6417915bf8ebeb43cbc11acbcd803701c0d0b5327e65c4c6d",
"cross_cats_sorted": [
"cs.SY"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "eess.SY",
"submitted_at": "2026-05-13T09:48:44Z",
"title_canon_sha256": "947aecb07d926e6048f5fd802c2c57f334eef73060c6b60109e77630a16d670d"
},
"schema_version": "1.0",
"source": {
"id": "2605.13269",
"kind": "arxiv",
"version": 1
}
}