Pith Number

pith:5AKCLSOE

pith:2020:5AKCLSOEPX7ZECUB2MCPVE5A72

not attested not anchored not stored refs resolved

Mastering Atari with Discrete World Models

Danijar Hafner, Jimmy Ba, Mohammad Norouzi, Timothy Lillicrap

DreamerV2 achieves human-level performance on Atari by learning behaviors inside a separately trained discrete world model.

arxiv:2010.02193 v4 · 2020-10-05 · cs.LG · cs.AI · 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{5AKCLSOEPX7ZECUB2MCPVE5A72}

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

DreamerV2 constitutes the first agent that achieves human-level performance on the Atari benchmark of 55 tasks by learning behaviors inside a separately trained world model.

C2weakest assumption

That the learned discrete world model remains sufficiently accurate over the multi-step imagined trajectories used for policy optimization, without compounding errors that would invalidate the imagined returns.

C3one line summary

DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.

References

56 extracted · 56 resolved · 41 Pith anchors

[1] H., and Levine, S · arXiv:1710.11252

[2] Agent57: Outperforming the Atari Human Benchmark 2003

[3] A distributional perspective on rein- forcement learning.arXiv preprint arXiv:1707.06887 · arXiv:1707.06887

[4] Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation · arXiv:1308.3432

[5] Learning and Querying Fast Generative Models for Reinforcement Learning · arXiv:1802.03006

Formal links

2 machine-checked theorem links

Cited by

44 papers in Pith

GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation

Physically Interpretable World Models via Weakly Supervised Representation Learning

stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation

Generative Recursive Reasoning

Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds

Receipt and verification

First computed	2026-05-17T23:39:05.133505Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e81425c9c47dff920a81d304fa93a0febb85398e4b4caafbd2e82996b0336154

Aliases

arxiv: 2010.02193 · arxiv_version: 2010.02193v4 · doi: 10.48550/arxiv.2010.02193 · pith_short_12: 5AKCLSOEPX7Z · pith_short_16: 5AKCLSOEPX7ZECUB · pith_short_8: 5AKCLSOE

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/5AKCLSOEPX7ZECUB2MCPVE5A72 \
  | 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: e81425c9c47dff920a81d304fa93a0febb85398e4b4caafbd2e82996b0336154

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5ce5127337c9fa31dec90f012feca927d55fef23576a1fc97d5066dd02ea866b",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2020-10-05T17:52:14Z",
    "title_canon_sha256": "603fc9f15cf6bed973e38f100f387b0308723a9449bd143904c5590fc7ef33ee"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2010.02193",
    "kind": "arxiv",
    "version": 4
  }
}