Pith Number

pith:D2SNJQKL

pith:2020:D2SNJQKLI5QUGBTXUQYQSF73PR

not attested not anchored not stored refs resolved

D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Aviral Kumar, George Tucker, Justin Fu, Ofir Nachum, Sergey Levine

New benchmark datasets for offline RL, drawn from human demonstrations and mixed policies, expose deficiencies in existing algorithms.

arxiv:2004.07219 v4 · 2020-04-15 · cs.LG · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{D2SNJQKLI5QUGBTXUQYQSF73PR}

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 moving beyond simple benchmark tasks and data collected by partially-trained RL agents, we reveal important and unappreciated deficiencies of existing algorithms.

C2weakest assumption

That datasets generated via hand-designed controllers, human demonstrators, multitask settings, and mixtures of policies capture the key properties most relevant to real-world offline RL applications.

C3one line summary

D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.

References

24 extracted · 24 resolved · 7 Pith anchors

[1] Preprint arXiv:1908.00261 , year= 1908

[2] Scaling data-driven robotics with reward sketching and batch reinforcement learning.Preprint arXiv:1909.12200 1909

[3] End- to-end driving via conditional imitation learning 2018

[4] Challenges of Real-World Reinforcement Learning 1904 · arXiv:1904.12901

[5] Mankowitz, Jerry Li, Cosmin Paduraru, Sven Gowal, and Todd Hes- ter 2003

Formal links

1 machine-checked theorem link

Cited by

98 papers in Pith

Fitted Occupancy-Ratio Evaluation without Bellman Completeness

Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition

OnDeFog: Online Decision Transformer under Frame Dropping

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

PAWS: Preference Learning with Advantage-Weighted Segments

Receipt and verification

First computed	2026-07-05T02:13:13.910791Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1ea4d4c14b4761430677a4310917fb7c736cb2b5838d04c44cb6c94c99428dbc

Aliases

arxiv: 2004.07219 · arxiv_version: 2004.07219v4 · doi: 10.48550/arxiv.2004.07219 · pith_short_12: D2SNJQKLI5QU · pith_short_16: D2SNJQKLI5QUGBTX · pith_short_8: D2SNJQKL

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/D2SNJQKLI5QUGBTXUQYQSF73PR \
  | 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: 1ea4d4c14b4761430677a4310917fb7c736cb2b5838d04c44cb6c94c99428dbc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5512cf4724e468ca0a0f4414d6d074c3f6cdb4aae9db977fb8f204e54855c16b",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2020-04-15T17:18:19Z",
    "title_canon_sha256": "35a4c1a61624d1cfe16366f887d9938531d3185d83679fea4470f32dcc26b27f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2004.07219",
    "kind": "arxiv",
    "version": 4
  }
}