Pith Number

pith:7J4XWRSD

pith:2025:7J4XWRSDFT6BX7NHEVJPLVE7DH

not attested not anchored not stored refs pending

Distributional Inverse Reinforcement Learning

Anqi Wu, Feiyang Wu, Ye Zhao

A distributional framework for offline inverse reinforcement learning recovers full reward distributions and distribution-aware policies by minimizing first-order stochastic dominance violations.

arxiv:2510.03013 v4 · 2025-10-03 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7J4XWRSDFT6BX7NHEVJPLVE7DH}

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

our method captures richer structure in expert behavior, particularly in learning the reward distribution, by minimizing first-order stochastic dominance (FSD) violations and thus integrating distortion risk measures (DRMs) into policy learning, enabling the recovery of both reward distributions and distribution-aware policies

C2weakest assumption

The central claim rests on the premise that minimizing FSD violations is sufficient to integrate DRMs into policy learning and recover meaningful reward distributions from offline expert data without additional assumptions on the form of the return distributions or the coverage of the offline dataset.

C3one line summary

A distributional offline IRL method minimizes first-order stochastic dominance violations to recover reward distributions and distribution-aware policies, with O(ε^{-2}) convergence and reported SOTA results on synthetic, neurobehavioral, and MuJoCo tasks.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-29T01:04:35.844781Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fa797b46432cfc1bfda72552f5d49f19cf328e4dd4326e928877c4e960b51235

Aliases

arxiv: 2510.03013 · arxiv_version: 2510.03013v4 · doi: 10.48550/arxiv.2510.03013 · pith_short_12: 7J4XWRSDFT6B · pith_short_16: 7J4XWRSDFT6BX7NH · pith_short_8: 7J4XWRSD

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/7J4XWRSDFT6BX7NHEVJPLVE7DH \
  | 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: fa797b46432cfc1bfda72552f5d49f19cf328e4dd4326e928877c4e960b51235

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f608370f8740778d3a53aed4e80ba9c3893ffbf091453bf623aa18487071c81e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-10-03T13:58:09Z",
    "title_canon_sha256": "fa091c46ada164eced69db379723da4bd2b33f4dab9996410db74c9563c8e6fd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.03013",
    "kind": "arxiv",
    "version": 4
  }
}