SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09243 · NeurIPS · 2024

DiffClone: Enhanced Behaviour Cloning in Robotics with Diffusion-Driven Policy Learning

Sabariswaran Mani, Sreyas Venkataraman, Abhranil Chandra, Yash Sirvi, Adyan Rizvi, Soumojit Bhattacharya, Aritra Hazra

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2401.09243.json · badge: /api/ran/2401.09243.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
sirabas369/DiffClone canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_accuracy Ran
ran, honoured the contract we drafted
sirabas369/DiffClone/toto_benchmark/vision/pvr_model_training.py
code served (permissive licence) · get_code("1263c50ebe6172a3")
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 float, ndim 0, dtype family float, shape () 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 as nn

torch.manual_seed(0)

# Build a minimal model that satisfies the function's usage
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, batch):
        # The function expects model(batch) to return a tensor
        # that can be compared with batch['actions'] via MSELoss
        return self.linear(batch['observations'])

# Create a minimal dataloader (iterable of batches)
class SimpleDataLoader:
    def __init__(self, num_batches=5):
        self.num_batches = num_batches
        self.current = 0
    
    def __iter__(self):
        self.current = 0
        return self
    
    def __next__(self):
        if self.current >= self.num_batches:
            raise StopIteration
        self.current += 1
        # Return a batch with 'observations' and 'actions' keys
        batch = {
            'observations': torch.randn(2, 4),  # batch_size=2, feature_dim=4
            'actions': torch.randn(2, 3)  # batch_size=2, action_dim=3
        }
        return batch

# Build the dataloader as an infinite iterator
dataloader = SimpleDataLoader(num_batches=10)

# Build the model
model = SimpleModel()

# Build the config
config = {
    'device': 'cpu',
    'eval_steps': 5
}

ARGS = {
    'dataloader': dataloader,
    'model': model,
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
get_stats Ran
ran; our contract draft was wrong, not the code
sirabas369/DiffClone/toto_benchmark/agents/Diffusion_Agent_Unet.py
code served (permissive licence) · get_code("62608541281b5cad")
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 torch
import numpy as np

torch.manual_seed(0)

# The function expects arr to have:
# - .std(0) method (standard deviation along axis 0)
# - .mean(0) method (mean along axis 0)
# - len() support
# The result should be indexable and support comparison with 0.0001

# Create a small numpy array (batch_size=2, features=4)
arr = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "arr": arr
}
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 — 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
get_time_chunk Ran
ran, honoured the contract we drafted
sirabas369/DiffClone/toto_benchmark/vision/pvr_model_training.py
code served (permissive licence) · get_code("9b85e2ca522ca849")
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 float, shape (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 mock path dictionary containing numpy arrays
path = {
    'feature_1': np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0]),
    'feature_2': np.array([10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 80.0]),
}

ARGS = {
    'path': path,
    'key': 'feature_1',
    't': 5,
    'window': 3,
}
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 float, shape (3,) — shape (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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 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
compute_accuracy 1 other paper
1 dated earlier
2306.00942 (2023-06)
Train Offline, Test Online: A Real Robot Learning Benchmark
get_stats 1 other paper
1 dated earlier
2306.00942 (2023-06)
Train Offline, Test Online: A Real Robot Learning Benchmark
get_time_chunk 1 other paper
1 dated earlier
2306.00942 (2023-06)
Train Offline, Test Online: A Real Robot Learning Benchmark

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

Robot learning tasks are extremely compute-intensive and hardware-specific. Thus the avenues of tackling these challenges, using a diverse dataset of offline demonstrations that can be used to train robot manipulation agents, is very appealing. The Train-Offline-Test-Online (TOTO) Benchmark provides a well-curated open-source dataset for offline training comprised mostly of expert data and also benchmark scores of the common offline-RL and behaviour cloning agents. In this paper, we introduce DiffClone, an offline algorithm of enhanced behaviour cloning agent with diffusion-based policy learning, and measured the efficacy of our method on real online physical robots at test time. This is also our official submission to the Train-Offline-Test-Online (TOTO) Benchmark Challenge organized at NeurIPS 2023. We experimented with both pre-trained visual representation and agent policies. In our experiments, we find that MOCO finetuned ResNet50 performs the best in comparison to other finetuned representations. Goal state conditioning and mapping to transitions resulted in a minute increase in the success rate and mean-reward. As for the agent policy, we developed DiffClone, a behaviour cloning agent improved using conditional diffusion.

For agents

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

get_harvested_code_for_paper("2401.09243")
get_code_for_paper("2401.09243")
have("2401.09243")

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

curl https://syntology.ai/api/ran/2401.09243.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.09243.svg)](https://syntology.ai/paper/2401.09243)

Connect an agent — have() is free.