Pith Number

pith:2Z4HA2PY

pith:2026:2Z4HA2PYVJWBCYBRQ35KIQYBOR

not attested not anchored not stored refs resolved

Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning

Gwanwoo Choi, Jeongmo Kim, Minung Kim, Seungyul Han

Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL.

arxiv:2605.13054 v1 · 2026-05-13 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{2Z4HA2PYVJWBCYBRQ35KIQYBOR}

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

TCE builds on a dual score-based generative model to synthesize target-consistent transitions over an expanded state region. Extensive experiments across diverse cross-domain environments show that TCE consistently outperforms state-of-the-art cross-domain offline RL baselines.

C2weakest assumption

The dual score-based generative model can reliably synthesize target-consistent transitions over an expanded state region without introducing harmful distribution shifts.

C3one line summary

TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments.

References

43 extracted · 43 resolved · 6 Pith anchors

[1] arXiv preprint arXiv:1805.12298 , year= 2018 · arXiv:1805.12298

[2] A survey of au- tonomous driving: Common practices and emerging technologies.IEEE access, 8:58443–58469, 2020 2020

[3] Off-dynamics reinforcement learning: Training for transfer with domain classifiers 2020

[4] Domain adaptive imitation learning 2020

[5] Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems 2005 · arXiv:2005.01643

Receipt and verification

First computed	2026-05-18T03:08:59.244109Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699

Aliases

arxiv: 2605.13054 · arxiv_version: 2605.13054v1 · doi: 10.48550/arxiv.2605.13054 · pith_short_12: 2Z4HA2PYVJWB · pith_short_16: 2Z4HA2PYVJWBCYBR · pith_short_8: 2Z4HA2PY

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/2Z4HA2PYVJWBCYBRQ35KIQYBOR \
  | 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: d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b8ab930630e8062a1fdfaa0e4ea4433c7441496f9efa1bad71dc9087f16c0120",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T06:23:51Z",
    "title_canon_sha256": "b017bebe7100461cc0ad9252248770b7a341540de6f88e3814a4b4fbb384a6c1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13054",
    "kind": "arxiv",
    "version": 1
  }
}