Pith Number

pith:OLP63MQO

pith:2026:OLP63MQOF4LHYFUEL6YGVXI3JS

not attested not anchored not stored refs resolved

Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human Feedback

Dongming Wang, He Wang, Jian Qin, Pengcheng Dai, Wenwu Yu

Agents in a network can learn collaborative policies from local human feedback on short trajectory pairs without needing global states or reward signals.

arxiv:2605.15697 v1 · 2026-05-15 · cs.MA

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{OLP63MQOF4LHYFUEL6YGVXI3JS}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We further rigorously establish that the proposed algorithm converges to an ε-stationary point with polynomial sample complexity.

C2weakest assumption

The human preference feedback generated from spatiotemporally truncated trajectories (H-horizon pairs aggregated over each agent's κ-hop neighborhood) depends solely on local state-action information and can be used to produce unbiased estimates of each agent's local policy gradient without requiring global state or explicit rewards.

C3one line summary

A distributed zeroth-order policy gradient algorithm allows networked agents to collaboratively optimize policies using only local human preference feedback on H-horizon trajectory pairs from kappa-hop neighborhoods, with proven convergence to an epsilon-stationary point.

References

36 extracted · 36 resolved · 1 Pith anchors

[1] Dai, P., Yu, W., Wen, G., & Baldi, S. (2020). Distributed reinforcement learning algorithm for dynamic economic dispatch with unknown generation cost functions. IEEE Transactions on Industrial Informa 2020

[2] Li, F., Qin, J., & Zheng, W. (2020). Distributed Q -learning-based online optimization algorithm for unit commitment and dispatch in smart grid. IEEE Transactions on Cybernetics, 50(9), 4146-4156 2020

[3] Dai, P., Yu, W., & Chen, D. (2022). Distributed Q-learning algorithm for dynamic resource allocation with unknown objective functions and application to microgrid. IEEE Transactions on Cybernetics, 52 2022

[4] Chu, T., Wang, J., Codec\` a , L., & Li, Z. (2020). Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Transactions on Intelligent Transportation Systems, 21(3), 1086 2020

[5] Wang, X., Ke, L., Qiao, Z., & Chai, X. (2021). Large-scale traffic signal control using a novel multiagent reinforcement learning. IEEE Transactions on Cybernetics, 51(1), 174-187 2021

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:13.055965Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

72dfedb20e2f167c16845fb06add1b4c9c911b84523986ca347a5614f516c260

Aliases

arxiv: 2605.15697 · arxiv_version: 2605.15697v1 · doi: 10.48550/arxiv.2605.15697 · pith_short_12: OLP63MQOF4LH · pith_short_16: OLP63MQOF4LHYFUE · pith_short_8: OLP63MQO

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/OLP63MQOF4LHYFUEL6YGVXI3JS \
  | 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: 72dfedb20e2f167c16845fb06add1b4c9c911b84523986ca347a5614f516c260

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "006016a9eced51157013869d7de6a7d2da1b2fa238e23ef597a47208063461c4",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.MA",
    "submitted_at": "2026-05-15T07:41:41Z",
    "title_canon_sha256": "7af84afdb813ba905d2eb1e6e8a49edbc5645b0cbfd8d8ac577d572a77ecc8dd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15697",
    "kind": "arxiv",
    "version": 1
  }
}