pith:DTUPU4YP
When Does Non-Uniform Replay Matter in Reinforcement Learning?
Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high.
arxiv:2605.10236 v3 · 2026-05-11 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{DTUPU4YPWBVOSXHAUETU2SFEGN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. ... non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency.
That the three identified factors comprehensively govern non-uniform replay effectiveness and that the observed benefits will generalize beyond the specific algorithms, benchmarks, and parallel-simulation regimes tested.
Non-uniform replay improves RL sample efficiency mainly in low replay-volume regimes, with high-entropy sampling being key even at comparable recency.
Receipt and verification
| First computed | 2026-05-20T00:04:35.665186Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/DTUPU4YPWBVOSXHAUETU2SFEGN \
| 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: 1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "620bf1ffe50dbaacaa7a9d4a62ea8c89e696204990ecc4b3b8aa6e570113787f",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-11T09:11:05Z",
"title_canon_sha256": "c552ff302da0820dc38cc0a64a17100907ea6d70298f50f5faaf1c656cedb6a3"
},
"schema_version": "1.0",
"source": {
"id": "2605.10236",
"kind": "arxiv",
"version": 3
}
}