SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.15256 · NeurIPS · 2022

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

Daesol Cho, Dongseok Shim, H Kim

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 3 failures of our instrument; 1 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/2209.15256.json · badge: /api/ran/2209.15256.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
dsshim0125/s2p canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
add_prefix Ran
ran; our contract draft was wrong, not the code
dsshim0125/s2p/rlkit/core/logging.py
pointer only (licence: MIT); the stored copy get_code serves, from shlee94/Off2OnRL, is pointer only (licence: NONE) · get_code("6dc14f1205c31904")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shlee94/Off2OnRL, and GitHub detected no licence in that repository when it was checked. 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.

create_stats_ordered_dict Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dsshim0125/s2p/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from aviralkumar2907/CQL, is pointer only (licence: NONE) · get_code("fadf5f762ff04cd6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aviralkumar2907/CQL, and GitHub detected no licence in that repository when it was checked. 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.

get_average_returns Ran
ran, honoured the contract we drafted
dsshim0125/s2p/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from aviralkumar2907/CQL, is pointer only (licence: NONE) · get_code("a5d10a0b704c8db7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aviralkumar2907/CQL, and GitHub detected no licence in that repository when it was checked. 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_image Ran
ran on a synthesized input
dsshim0125/s2p/multiworld_custom/core/image_env.py
code served (permissive licence) · get_code("f725932e0f8878f4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small uint8 image (2D array with shape 4x3)
image = np.array([
    [0, 128, 255],
    [64, 192, 32]
], dtype=np.uint8)

# Define arguments for normalize_image
ARGS = {
    "image": image,
    "dtype": np.float64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
soft_clamp Ran
ran; our contract draft was wrong, not the code
dsshim0125/s2p/gaussian_ensemble.py
code served (permissive licence) · get_code("3b4df5488a40f1ca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Define min and max values
_min = torch.tensor(-1.0)
_max = torch.tensor(1.0)

ARGS = {
    "x": x,
    "_min": _min,
    "_max": _max,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
unormalize_image Ran
ran on a synthesized input
dsshim0125/s2p/multiworld_custom/core/image_env.py
code served (permissive licence) · get_code("57b9f4dd9833bb0b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (2, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small unnormalized image (float values in range [0, 1])
# Using shape (2, 3, 4) for a small 2x3x4 image with 3 channels
image = np.random.rand(2, 3, 4).astype(np.float32)

ARGS = {
    "image": image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (2, 3, 4) — shape (2, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
append_log Not yet run
unverified (harvested, no recorded run)
dsshim0125/s2p/rlkit/core/logging.py
pointer only (licence: MIT); the stored copy get_code serves, from shlee94/Off2OnRL, is pointer only (licence: NONE) · get_code("46e6d80fdfab6884")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shlee94/Off2OnRL, and GitHub detected no licence in that repository when it was checked. 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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
get_average_returns 24 other papers
12 dated earlier, 12 later
1903.08254 (2019-03)
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
1912.11032 (2019-12)
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
and 21 more not named here
create_stats_ordered_dict 18 other papers
8 dated earlier, 10 later
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
2006.04779 (2020-06)
Conservative Q-Learning for Offline Reinforcement Learning
2006.13916 (2020-06)
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
and 15 more not named here
add_prefix 10 other papers
4 dated earlier, 6 later
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
2106.00671 (2021-06)
What Can I Do Here? Learning New Skills by Imagining Visual Affordances
2110.03655 (2021-10)
Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
and 7 more not named here
append_log 9 other papers
4 dated earlier, 5 later
1910.12827 (2019-10)
Entity Abstraction in Visual Model-Based Reinforcement Learning
2006.07034 (2020-06)
Benchmarking Unsupervised Object Representations for Video Sequences
2110.03655 (2021-10)
Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
and 6 more not named here
soft_clamp 2 other papers
2 later
2405.17031 (2024-05)
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
2410.11234 (2024-10)
Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning
normalize_image 1 other paper
1 dated earlier
1910.10897 (2019-10)
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
unormalize_image 1 other paper
1 dated earlier
1910.10897 (2019-10)
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

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

Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training. To alleviate such limitation, state-based offline RL leverages a learned dynamics model from the logged experience and augments the predicted state transition to extend the data distribution. For exploiting such benefit also on the image-based RL, we firstly propose a generative model, S2P (State2Pixel), which synthesizes the raw pixel of the agent from its corresponding state. It enables bridging the gap between the state and the image domain in RL algorithms, and virtually exploring unseen image distribution via model-based transition in the state space. Through experiments, we confirm that our S2P-based image synthesis not only improves the imagebased offline RL performance but also shows powerful generalization capability on unseen tasks.

For agents

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

get_harvested_code_for_paper("2209.15256")
get_code_for_paper("2209.15256")
have("2209.15256")

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

curl https://syntology.ai/api/ran/2209.15256.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.15256.svg)](https://syntology.ai/paper/2209.15256)

Connect an agent — have() is free.