pith:RAPIYXPD
The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
Setting learning phases equal to the horizon H allows polynomial agents to approximate MDP dynamics in multi-agent reward-free exploration.
arxiv:2602.01453 v3 · 2026-02-01 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{RAPIYXPD3W32G56UPIHWZUPXH7}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
When the number of learning phases equals H, we present a computationally efficient algorithm that uses only Õ(S^6 H^6 A / ε²) agents to obtain an ε approximation of the dynamics (i.e., yields an ε-optimal policy for any reward function). We complement our algorithm with a lower bound showing that any algorithm restricted to ρ < H phases requires at least A^{H/ρ} agents to achieve constant accuracy.
The MDP is tabular and finite-horizon, and the learning proceeds in independent phases where each agent is assigned a policy and executes it without intra-phase communication.
Θ(H) learning phases are necessary and sufficient for polynomial-agent ε-accurate dynamics estimation in multi-agent reward-free exploration of finite-horizon tabular MDPs.
Cited by
Receipt and verification
| First computed | 2026-05-18T03:09:24.033584Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
881e8c5de3ddb7a377d47a0f6cd1f73fc67feb293447cad0304f97dfb52f3891
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/RAPIYXPD3W32G56UPIHWZUPXH7 \
| 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: 881e8c5de3ddb7a377d47a0f6cd1f73fc67feb293447cad0304f97dfb52f3891
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "3d0557f081da79de65c4311622df0fb86b19b47ef16d67a1b66d86da095ae2db",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-02-01T21:44:11Z",
"title_canon_sha256": "86271ab381b69e0d5f4c664f5e0125f946e799b1753f745e712a834545ba03ba"
},
"schema_version": "1.0",
"source": {
"id": "2602.01453",
"kind": "arxiv",
"version": 3
}
}