Papers › Mastering Diverse Domains through World Models

Mastering Diverse Domains through World Models

10 Jan 2023arXiv:2301.04104archive 2025-07-28

Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap

Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement learning algorithms can be readily applied to tasks similar to what they have been developed for, configuring them for new application domains requires significant human expertise and experimentation. We present DreamerV3, a general algorithm that outperforms specialized methods across over 150 diverse tasks, with a single configuration. Dreamer learns a model of the environment and improves its behavior by imagining future scenarios. Robustness techniques based on normalization, balancing, and transformations enable stable learning across domains. Applied out of the box, Dreamer is the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula. This achievement has been posed as a significant challenge in artificial intelligence that requires exploring farsighted strategies from pixels and sparse rewards in an open world. Our work allows solving challenging control problems without extensive experimentation, making reinforcement learning broadly applicable.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (danijar/dreamerv3) is linked to this paper; the 34 samples below come from 1 community repository. Syntology harvested code from danijar/dreamerv3 for another paper.

danijar/dreamerv3: Syntology's graph links these samples to Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning (arXiv:2606.20411; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 34 code samples harvested from 1 repository linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 34 samples from 1 repository, 21 ran (16 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

danijar/dreamerv3 officialmentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning (arXiv:2606.20411; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Alescontrela/viper_rl mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video Prediction Models as Rewards for Reinforcement Learning (arXiv:2305.14343; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
alescontrela/viper mentioned on GitHubjaxMITSyntology: not harvested report
glambrechts/informed-dreamer mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Informed POMDP: Leveraging Additional Information in Model-Based RL (arXiv:2306.11488; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
nm512/dreamerv3-torch mentioned on GitHubpytorchSyntology: 34 samples, 21 ran (5 instrument-failed) · 13 unverified report
opendilab/DI-engine mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
danijar/daydreamer pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

34 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
16ran
13unverified

Licence: 0 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nm512/dreamerv3-torch. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

nm512/dreamerv3-torch community (archive-listed) 34 samples, 21 ran (5 instrument-failed) · 13 unverified
Bernoulli in 7 papers dreamer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e681676cbd727836 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ContDist dreamer.py ran · metamorphic tier: well formed MIT (permissive) · 176de01fbad3023e · report fixture: signature sample_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
Conv2dSamePad dreamer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · ffedbf10704bc84d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ConvEncoder in 12 papers dreamer.py ran MIT (permissive) · 8097025bbaf735ac · report fixture: signature obs:Tensor/4/float · returned Tensor · level recorded 2026-09-24
DiscDist dreamer.py ran · metamorphic tier: invariant MIT (permissive) · 40c192080c59445f · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Every dreamer.py ran · metamorphic tier: well formed fingerprinted MIT (permissive) · b8806e5208586490 · report fixture: signature step:int/0/int · returned int · level recorded 2026-09-22
GRUCell in 7 papers dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · b277728e34839765 · report fixture: signature inputs:Tensor/2/float, state:list/1/Tensor · returned tuple · level recorded 2026-09-22
ImgChLayerNorm dreamer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 91cc12a004a18d4b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MSEDist dreamer.py ran fingerprinted MIT (permissive) · 8addd6348ab08f08 · report fixture: signature value:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Once dreamer.py ran MIT (permissive) · 72e56ebf38efd993 · report fixture: returned bool · level recorded 2026-09-24
OneHotDist dreamer.py ran MIT (permissive) · 8fe729e5b488314a · report fixture: signature sample_shape:tuple/1/int, seed:NoneType/0/? · returned Tensor · level recorded 2026-09-24
Random dreamer.py ran MIT (permissive) · 60858ba7201fa411 · report fixture: signature start:Tensor/2/float, context:Tensor/2/float, data:Tensor/2/float · returned tuple · level recorded 2026-09-24
SafeTruncatedNormal dreamer.py ran MIT (permissive) · 81392766dd9e5f90 · report fixture: signature sample_shape:Size/1/int · returned Tensor · level recorded 2026-09-24
SymlogDist dreamer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · b88fb85f59d2ee19 · report fixture: signature value:Tensor/2/float · returned Tensor · level recorded 2026-09-22
TanhBijector dreamer.py ran fingerprinted MIT (permissive) · ccb38fe3b67c3f47 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
Until dreamer.py ran fingerprinted MIT (permissive) · 3d7ec6f83d9cefcf · report fixture: signature step:int/0/int · returned bool · level recorded 2026-09-24
lambda_return in 7 papers dreamer.py ran · our draft was wrong MIT (permissive) · 3d3a2f5348d90046 · report fixture: signature reward:Tensor/3/float, value:Tensor/3/float, pcont:float/0/float, bootstrap:NoneType/0/?, lambda_:float/0/float, axis:int/0/int · returned tuple · level recorded 2026-09-24
symexp in 20 papers dreamer.py ran · our draft was wrong fingerprinted MIT (permissive) · fd421307a7e4cede · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
symlog in 24 papers
census: 5 implementations from 7 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
dreamer.py ran · our draft was wrong fingerprinted MIT (permissive) · 3e346b9b00ea8169 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
tensorstats in 10 papers dreamer.py ran · our draft was wrong fingerprinted MIT (permissive) · 37981558f2b7669b · report fixture: signature tensor:Tensor/2/float, prefix:str/0/str · returned dict · level recorded 2026-09-22
uniform_weight_init dreamer.py ran · our draft was wrong MIT (permissive) · 8ab3c3275de4031e · report fixture: signature given_scale:float/0/float · returned function · level recorded 2026-09-22
ConvDecoder in 6 papers dreamer.py unverified MIT (permissive) · bd06b32e32cc8750 · report
Dreamer dreamer.py unverified MIT (permissive) · 0109f7f0801c59db · report
ImagBehavior dreamer.py unverified MIT (permissive) · 51adcb05639dfb9c · report
MLP in 375 papers dreamer.py unverified MIT (permissive) · 02f11645dd0babdb · report
MultiDecoder dreamer.py unverified MIT (permissive) · 034c39a2bc2a4cdd · report
MultiEncoder dreamer.py unverified MIT (permissive) · c00542f5f0dde998 · report
Optimizer in 18 papers dreamer.py unverified MIT (permissive) · ad4473538a000c98 · report
Plan2Explore dreamer.py unverified MIT (permissive) · e16338beac400c5e · report
RSSM in 7 papers dreamer.py unverified MIT (permissive) · 795c1fe9da508672 · report
RewardEMA dreamer.py unverified MIT (permissive) · d6d8a159b73de69a · report
SampleDist dreamer.py unverified MIT (permissive) · c8caad78f3b4ea79 · report
WorldModel in 13 papers dreamer.py unverified MIT (permissive) · 536e51c6e29f6a5b · report
weight_init in 73 papers dreamer.py unverified MIT (permissive) · 9aaedf6b6e636015 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DreamerV3 (graph method: DreamerV3). 38 bricks; individually on a fixture: 23 ran (of which 1 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified. The assembly has not been run end-to-end.

  1. Dreamer entry · level 0 · unverified · 0109f7f0801c59db
  2. Every helper · level 1 · ran · b8806e5208586490
  3. ImagBehavior model · level 0 · unverified · 51adcb05639dfb9c
  4. Once helper · level 1 · ran · 72e56ebf38efd993
  5. Plan2Explore sampler · level 0 · unverified · e16338beac400c5e
  6. Random helper · level 1 · ran · 60858ba7201fa411
  7. Until helper · level 1 · ran · 3d7ec6f83d9cefcf
  8. WorldModel model · level 0 · unverified · 536e51c6e29f6a5b
  9. MLP helper · level 0 · unverified · 02f11645dd0babdb
  10. Optimizer helper · level 0 · unverified · ad4473538a000c98
  11. RequiresGrad helper · level 1 · ran · eb6cf9a53f925599
  12. RewardEMA helper · level 0 · unverified · d6d8a159b73de69a
  13. lambda_return helper · level 1 · ran · our draft was wrong · 3d3a2f5348d90046
  14. static_scan helper · level 0 · unverified · 514d05952ec692b5
  15. tensorstats helper · level 1 · ran · our draft was wrong · 37981558f2b7669b
  16. OneHotDist helper · level 1 · ran · 8fe729e5b488314a
  17. MultiDecoder model · level 0 · unverified · 034c39a2bc2a4cdd
  18. MultiEncoder model · level 0 · unverified · c00542f5f0dde998
  19. RSSM model · level 0 · unverified · 795c1fe9da508672
  20. Bernoulli helper · level 1 · ran · e681676cbd727836
  21. ContDist helper · level 1 · ran · 176de01fbad3023e
  22. DiscDist helper · level 1 · ran · 40c192080c59445f
  23. SafeTruncatedNormal helper · level 1 · ran · 81392766dd9e5f90
  24. SampleDist helper · level 0 · unverified · c8caad78f3b4ea79
  25. SymlogDist helper · level 1 · ran · b88fb85f59d2ee19
  26. TanhBijector helper · level 1 · ran · ccb38fe3b67c3f47
  27. UnnormalizedHuber helper · level 1 · ran · 2445794b39372705
  28. symlog helper · level 1 · ran · our draft was wrong · 3e346b9b00ea8169
  29. uniform_weight_init helper · level 1 · ran · our draft was wrong · 8ab3c3275de4031e
  30. weight_init helper · level 0 · unverified · 9aaedf6b6e636015
  31. static_scan_for_lambda_return helper · level 0 · unverified · 9db8ef02611811ce
  32. ConvDecoder helper · level 0 · unverified · bd06b32e32cc8750
  33. MSEDist helper · level 1 · ran · 8addd6348ab08f08
  34. ConvEncoder helper · level 1 · ran · 8097025bbaf735ac
  35. GRUCell helper · level 1 · ran · b277728e34839765
  36. symexp helper · level 1 · ran · our draft was wrong · fd421307a7e4cede
  37. ImgChLayerNorm helper · level 1 · ran · 91cc12a004a18d4b
  38. Conv2dSamePad helper · level 1 · ran · ffedbf10704bc84d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2301.04104") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Atari Games 100kDecision MakingMinecraftReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections