SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.00588 · ICLR · 2023

Transformers are Sample Efficient World Models

Vincent Micheli, François Fleuret, Eloi Alonso

arXiv · PDF · Open in the Atlas

Code that ran

17 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (13 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 15 have no contract verdict; 1 failure of our instrument; 9 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2209.00588.json · badge: /api/ran/2209.00588.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
eloialonso/iris canonical (classifier label)
classifier basis: classifier_2025
17 ran · 9 no recorded run
FunctionStatusWhere it lives
AssignWithoutInplaceCheck Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("7f939e4da5014501")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AttnBlock Ran
ran on a synthesized input
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("9d1f4ad302b969e4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Cache Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("256e6e8e5c0039da")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Downsample Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("e8df5d8fcd9e9339")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Embedder Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("2def3130991aaf3c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EncoderDecoderConfig Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("cd65aa1097b08332")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Head Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("b4868fbed7dce84a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

KVCache Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("93bd9c4b1f02db59")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

KeysValues Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("fba3ef4043569d6f")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LossWithIntermediateLosses Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("d7a1b7c2fadc881a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Normalize Ran
ran; our contract draft was wrong, not the code
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("41ffde6c773af0d6")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Slicer Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("3e962c6d7a040002")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TokenizerEncoderOutput Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("bf4dc4c0382a6bd0")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TransformerConfig Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("06c7be0a3042efdc")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Upsample Ran
ran on a synthesized input
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("53918c7471cbccdc")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

WorldModelOutput Ran
ran on a synthesized input · constructed an object; no result was computed
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("419935433daf0f1b")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

nonlinearity Ran
ran, honoured the contract we drafted
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("3f6efbafceb71819")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Block Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("ee23a284027c25be")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Decoder Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("4e93d0d0e4839243")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Encoder Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("aee0695eaeb766c4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ResnetBlock Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("caffc15eb259ebb0")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

SelfAttention Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("f16fd90513419812")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Tokenizer Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("79b0b0b918ab2ac4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Transformer Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("d65bf756384c37cd")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

WorldModel Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("cfb3154cdccd72da")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

init_weights Not yet run
unverified (harvested, no recorded run)
eloialonso/iris/src/models/world_model.py
pointer only (licence: GPL-3.0) · get_code("7fc674de9a0a0a02")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, eloialonso/iris, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 12 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 12 later) and 14 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
nonlinearity
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2308.11408 (2023-08)
MatFuse: Controllable Material Generation with Diffusion Models
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
AttnBlock
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
Decoder
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
Downsample
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
Encoder
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
EncoderDecoderConfig
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
LossWithIntermediateLosses
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
Normalize
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
ResnetBlock
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
Tokenizer
brick of this paper's assembly: model
1 other paper
1 later
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
TokenizerEncoderOutput
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL
Upsample
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.01591 (2025-02)
Improving Transformer World Models for Data-Efficient RL

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the imagination of a world model being one of the most prominent approaches. However, while virtually unlimited interaction with a simulated environment sounds appealing, the world model has to be accurate over extended periods of time. Motivated by the success of Transformers in sequence modeling tasks, we introduce IRIS, a data-efficient agent that learns in a world model composed of a discrete autoencoder and an autoregressive Transformer. With the equivalent of only two hours of gameplay in the Atari 100k benchmark, IRIS achieves a mean human normalized score of 1.046, and outperforms humans on 10 out of 26 games, setting a new state of the art for methods without lookahead search. To foster future research on Transformers and world models for sample-efficient reinforcement learning, we release our code and models at https://github.com/eloialonso/iris.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2209.00588")
get_code_for_paper("2209.00588")
have("2209.00588")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2209.00588.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2209.00588.svg)](https://syntology.ai/paper/2209.00588)

Connect an agent — have() is free.