pith:K2Y4D3YR
Inpatient Overflow Management with Proximal Policy Optimization
Proximal policy optimization with atomic actions manages inpatient overflow decisions at the scale of twenty patient classes and twenty wards.
arxiv:2410.13767 v6 · 2024-10-17 · math.OC
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{K2Y4D3YRLY76RM3VYIM2AOG7M6}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Case studies on hospital systems with up to twenty patient classes and twenty wards demonstrate that our approach matches or outperforms existing benchmarks, including approximate dynamic programming, which is computationally infeasible beyond five wards.
The queueing-informed value function approximation and partially-shared policy network together preserve near-optimal performance for the original multi-patient combinatorial problem without introducing bias that grows with system size; this premise is invoked when the authors state that the enhancements improve policy evaluation and computational efficiency while still producing competitive policies.
A PPO reinforcement learning method using atomic actions, partially-shared policies, and queueing-informed value approximation scales inpatient overflow optimization to hospital systems with 20 patient classes and wards, matching or beating benchmarks where prior methods fail.
Receipt and verification
| First computed | 2026-06-03T01:05:43.070163Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
56b1c1ef115e3fe8b375c219a038df67860e81041c00644366688f66db3b8506
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/K2Y4D3YRLY76RM3VYIM2AOG7M6 \
| 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: 56b1c1ef115e3fe8b375c219a038df67860e81041c00644366688f66db3b8506
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "f8843f83610103134600994bad7a6cedcac5ec20f5d8948352799b317a146759",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
"primary_cat": "math.OC",
"submitted_at": "2024-10-17T17:04:08Z",
"title_canon_sha256": "6a6e394eb70340dc414747669196d8224736d0cfd4b3728c0619c8d4f80bad98"
},
"schema_version": "1.0",
"source": {
"id": "2410.13767",
"kind": "arxiv",
"version": 6
}
}