pith:4MRX7NOB
A Harmonic Mean Formulation of Average Reward Reinforcement Learning in SMDPs
A modified harmonic mean operator correctly computes average reward rates in non-stationary semi-Markov decision processes.
arxiv:2605.04880 v1 · 2026-05-06 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{4MRX7NOBILF4SALFR563EFL3K6}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
This paper presents a novel modified harmonic mean operator that correctly computes reward rates even under such conditions. This yields model-free learning algorithms that can work with SMDPs, while maintaining robustness to non-stationary reward and duration distributions over time.
That the ratio of cumulative reward to cumulative duration becomes incorrect under non-stationarity in infinite-horizon SMDPs, and that the proposed harmonic-mean modification resolves this without introducing new biases or requiring additional assumptions.
A modified harmonic mean operator correctly computes reward rates in non-stationary SMDPs for average-reward reinforcement learning.
References
Receipt and verification
| First computed | 2026-05-27T01:05:56.196465Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
e3237fb5c142cbc901658f7db2157b578a67911ba3a50e83bcc7beee2ceef328
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/4MRX7NOBILF4SALFR563EFL3K6 \
| 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: e3237fb5c142cbc901658f7db2157b578a67911ba3a50e83bcc7beee2ceef328
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "60af616fdd4a5193ed3e9f635c0f6ed443c4e093fdcbc3ed2ed8af45d4b67c00",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-06T13:16:42Z",
"title_canon_sha256": "578a55a5a8058c617a340c9f17a80a454c1dde2440bd51654a5a83092e8d6b25"
},
"schema_version": "1.0",
"source": {
"id": "2605.04880",
"kind": "arxiv",
"version": 1
}
}