SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1602.02867 · 2016

Value Iteration Networks

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 1 failure of our instrument; 3 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/1602.02867.json · badge: /api/ran/1602.02867.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
kentsommer/pytorch-value-iteration-networks community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
TheAbhiKumar/tensorflow-value-iteration-networks community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
zuoxingdong/VIN_PyTorch_Visdom reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zuoxingdong/VIN_PyTorch_Visdom/VIN.py
pointer only (licence: NONE) · get_code("6a211696e771f81a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zuoxingdong/VIN_PyTorch_Visdom 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.

extract_action Ran
ran on a synthesized input
kentsommer/pytorch-value-iteration-networks/dataset/make_training_data.py
code served (permissive licence) · get_code("8c7774a2e730f2d0")
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 1, dtype family int, shape (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

# The function expects a trajectory, which is a 2D numpy array
# where each row represents a state/position and columns represent dimensions
# The function uses np.diff to compute state differences, so we need at least 2 timesteps
# Let's create a simple trajectory with 5 timesteps and 2 spatial dimensions

traj = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [2.0, 0.0],
    [2.0, 1.0],
    [2.0, 2.0]
], dtype=np.float64)

ARGS = {
    "traj": traj
}
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 1, dtype family int, shape (4,) — shape (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
fmt_item Ran
ran on a synthesized input
TheAbhiKumar/tensorflow-value-iteration-networks/utils.py
code served (permissive licence) · get_code("1378c01acad9d099")
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 str. The image it ran in was not recorded. If your copy returns the same type 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

# Test with a scalar numpy array and a reasonable length parameter
scalar_array = np.array(3.14159)
length_param = 10

ARGS = {
    'x': scalar_array,
    'l': length_param
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
fmt_row Ran
ran on a synthesized input
TheAbhiKumar/tensorflow-value-iteration-networks/utils.py
code served (permissive licence) · get_code("2e2dbafccf41d3bd")
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 str. The image it ran in was not recorded. If your copy returns the same type 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

# Analyze what fmt_row expects:
# - width: an integer controlling column width for formatting
# - row: an iterable of items to format

# Create test data
width = 10
row = [3.14159, 42, np.array(2.71828), "hello"]

ARGS = {
    "width": width,
    "row": row,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
get_stats Ran
ran on a synthesized input
kentsommer/pytorch-value-iteration-networks/utility/utils.py
code served (permissive licence) · get_code("1cfb1314c17b4deb")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

# Create a small loss tensor (scalar)
loss = torch.tensor(0.5, requires_grad=True)

# Create predictions tensor: batch_size=2, num_classes=4
predictions = torch.randn(2, 4)

# Create labels tensor: batch_size=2 with class indices
labels = torch.tensor([0, 2])

ARGS = {
    'loss': loss,
    'predictions': predictions,
    'labels': labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
process_gridworld_data Ran
ran on a synthesized input
TheAbhiKumar/tensorflow-value-iteration-networks/data.py
code served (permissive licence) · get_code("af4d8a958998504d")
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 tuple. The image it ran in was not recorded. If your copy returns the same type 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
import scipy.io as sio
import tempfile
import os

# Create a temporary .mat file with the required data
temp_dir = tempfile.mkdtemp()
temp_mat_file = os.path.join(temp_dir, 'test_data.mat')

# Create synthetic data matching what the function expects
num_samples = 70  # Use 70 so that 6/7 * 70 = 60 for clean split
imsize_val = 8

# Create data with the right shapes and ranges
batch_im_data = np.random.randint(1, 256, size=(num_samples, imsize_val, imsize_val)).astype('float64')
batch_value_data = np.random.randint(1, 256, size=(num_samples, imsize_val, imsize_val)).astype('float64')
state_x_data = np.random.randint(0, imsize_val, size=(num_samples, 1)).astype('int8')
state_y_data = np.random.randint(0, imsize_val, size=(num_samples, 1)).astype('int8')
batch_label_data = np.random.randint(0, 2, size=(num_samples, 1)).astype('int8')

# Save to .mat file
sio.savemat(temp_mat_file, {
    'batch_im_data': batch_im_data,
    'batch_value_data': batch_value_data,
    'state_x_data': state_x_data,
    'state_y_data': state_y_data,
    'batch_label_data': batch_label_data
})

ARGS = {
    'input': temp_mat_file,
    'imsize': imsize_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
trace_path Ran
ran on a synthesized input
kentsommer/pytorch-value-iteration-networks/domains/gridworld.py
code served (permissive licence) · get_code("f33caf46d9c3c64e")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# The function uses pred as a dictionary-like object where it indexes with int(path[i])
# It also uses source and target as numeric values to compare with path elements
# Let's create a simple predecessor dictionary and valid source/target values

pred = {
    0: 1,
    1: 2,
    2: 3,
    3: 4,
    4: 5,
    5: 6
}

source = 1
target = 6

ARGS = {
    "pred": pred,
    "source": source,
    "target": target
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
flipkernel Not yet run
unverified (harvested, no recorded run)
TheAbhiKumar/tensorflow-value-iteration-networks/utils.py
code served (permissive licence) · get_code("7a8884331f1bb0a7")
How it ran

no invocation recorded.

make_data Not yet run
unverified (harvested, no recorded run)
kentsommer/pytorch-value-iteration-networks/dataset/make_training_data.py
code served (permissive licence) · get_code("920061d6774dae0c")
How it ran

no invocation recorded.

sample_trajectory Not yet run
unverified (harvested, no recorded run)
kentsommer/pytorch-value-iteration-networks/domains/gridworld.py
code served (permissive licence) · get_code("4c13b9d8be9b390d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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.

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

We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiable approximation of the value-iteration algorithm, which can be represented as a convolutional neural network, and trained end-to-end using standard backpropagation. We evaluate VIN based policies on discrete and continuous path-planning domains, and on a natural-language based search task. We show that by learning an explicit planning computation, VIN policies generalize better to new, unseen domains.

For agents

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

get_harvested_code_for_paper("1602.02867")
get_code_for_paper("1602.02867")
have("1602.02867")

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

curl https://syntology.ai/api/ran/1602.02867.json

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

[![Syntology run record](https://syntology.ai/api/ran/1602.02867.svg)](https://syntology.ai/paper/1602.02867)

Connect an agent — have() is free.