Pith Number

pith:JCNH7MBQ

pith:2022:JCNH7MBQRB5ZDOEHFXTPZLOG7C

not attested not anchored not stored refs resolved

Is Conditional Generative Modeling all you need for Decision-Making?

Abhi Gupta, Anurag Ajay, Joshua Tenenbaum, Pulkit Agrawal, Tommi Jaakkola, Yilun Du

Modeling a policy as a return-conditional diffusion model generates effective decisions directly from offline data and outperforms traditional offline RL.

arxiv:2211.15657 v4 · 2022-11-28 · 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{JCNH7MBQRB5ZDOEHFXTPZLOG7C}

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

By modeling a policy as a return-conditional diffusion model, we illustrate how we may circumvent the need for dynamic programming and subsequently eliminate many of the complexities that come with traditional offline RL.

C2weakest assumption

That a conditional diffusion model trained on offline data can accurately generate high-return action sequences without explicit value estimation or dynamic programming, and that benchmark outperformance generalizes beyond the tested environments.

C3one line summary

Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.

References

300 extracted · 300 resolved · 23 Pith anchors

[1] Scaling Learning Algorithms Towards

[2] Advances in neural information processing systems , volume=

[3] Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=

[4] and Osindero, Simon and Teh, Yee Whye , journal =

[5] Deep learning , author=. 2016 , publisher= 2016

Cited by

36 papers in Pith

Score-Based One-step MeanFlow Policy Optimization

Mechanisms of Misgeneralization in Physical Sequence Modeling

Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making

Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing

SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution

Receipt and verification

First computed	2026-05-17T23:38:51.082608Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

489a7fb030887b91b8872de6fcadc6f8b87855f59f5c3ab486edaaf393e970dd

Aliases

arxiv: 2211.15657 · arxiv_version: 2211.15657v4 · doi: 10.48550/arxiv.2211.15657 · pith_short_12: JCNH7MBQRB5Z · pith_short_16: JCNH7MBQRB5ZDOEH · pith_short_8: JCNH7MBQ

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/JCNH7MBQRB5ZDOEHFXTPZLOG7C \
  | 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: 489a7fb030887b91b8872de6fcadc6f8b87855f59f5c3ab486edaaf393e970dd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2ec5816298e1e26909b53be1c3017bb84c60ab23e0acb148dc691820cc37b4db",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2022-11-28T18:59:02Z",
    "title_canon_sha256": "830c7b0127d8123443276b4658f42327ff6028df4c72d6f7faa8322eb0799604"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2211.15657",
    "kind": "arxiv",
    "version": 4
  }
}