SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.13702 · 2022

DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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, 1 violated it and 3 have no contract verdict; 2 failures 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/2210.13702.json · badge: /api/ran/2210.13702.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
Denys88/rl_games canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_sigma_parametrization Ran
ran on a synthesized input
Denys88/rl_games/rl_games/algos_torch/models.py
code served (permissive licence) · get_code("3d08114056d317e1")
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 3, 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 torch.nn as nn

torch.manual_seed(0)

class DummyNetwork(nn.Module):
    def __init__(self, sigma_parametrization='exp', min_sigma=0.0, max_sigma=0.0, logstd_bounds=None):
        super().__init__()
        self.sigma_parametrization = sigma_parametrization
        self.min_sigma = min_sigma
        self.max_sigma = max_sigma
        self.logstd_bounds = logstd_bounds
    
    def forward(self, x):
        return x

# Test case 1: exp parametrization (default)
raw_tensor = torch.randn(2, 4)
network = DummyNetwork(
    sigma_parametrization='exp',
    min_sigma=0.1,
    max_sigma=0.0,
    logstd_bounds=(-2.0, 2.0)
)

ARGS = {
    'raw': raw_tensor,
    'network': network
}
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 tuple, ndim 3, 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
flatten_to_tuple Ran
ran on a synthesized input
Denys88/rl_games/rl_games/algos_torch/flatten.py
code served (permissive licence) · get_code("a2835ac0fa2b6640")
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 collections
from dataclasses import dataclass

torch.manual_seed(0)

# Test cases for flatten_to_tuple function
# The function takes a single parameter 'obj' which can be various types

# Create test objects of different types
test_string = "hello"
test_bytes = b"world"
test_list = [1, 2, 3]
test_tuple = (4, 5, 6)
test_dict = {"a": 1, "b": 2}
test_tensor = torch.randn(2, 4)
test_nested_list = [torch.randn(2, 4), "test", {"key": 42}]
test_nested_dict = {
    "tensors": [torch.randn(2, 4), torch.randn(3, 5)],
    "strings": ["a", "b"],
    "nested": {"x": torch.randn(1, 2)}
}
test_nested_tuple = (torch.randn(2, 4), "data", [1, 2])
test_mixed_dict = {
    "z_value": torch.randn(2, 4),
    "a_string": "hello",
    "m_list": [1, 2, 3]
}

ARGS = {
    "obj": test_dict
}
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 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
read_sigma_bounds Ran
ran on a synthesized input
Denys88/rl_games/rl_games/algos_torch/network_builder.py
code served (permissive licence) · get_code("75f087b5d3b3ee91")
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

# Construct a valid space_config dict
space_config = {
    'min_sigma': 0.1,
    'max_sigma': 0.5
}

ARGS = {
    'space_config': space_config
}
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
rescale_actions Ran
ran, violated the contract we drafted
Denys88/rl_games/rl_games/algos_torch/players.py
code served (permissive licence) · get_code("3393350fcd53af55")
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 1, dtype family float, 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - low: used in arithmetic (high - low) / 2.0 and (high + low) / 2.0
# - high: used in arithmetic (high - low) / 2.0 and (high + low) / 2.0
# - action: used in arithmetic action * d + m
# All parameters are numeric values/tensors used in element-wise operations

# Create small tensors for testing
low = torch.tensor([0.0, -1.0, -2.0, -3.0])
high = torch.tensor([1.0, 2.0, 3.0, 4.0])
action = torch.tensor([0.5, 0.0, -0.5, 1.0])

ARGS = {
    "low": low,
    "high": high,
    "action": action,
}
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 Tensor, ndim 1, dtype family float, 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
symexp Ran
ran; our contract draft was wrong, not the code
Denys88/rl_games/rl_games/algos_torch/layers.py
code served (permissive licence) · get_code("fd421307a7e4cede")
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) 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

torch.manual_seed(0)

# The function symexp takes a single parameter x and applies:
# torch.sign(x) * (torch.exp(torch.abs(x)) - 1.0)
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
symlog Ran
ran; our contract draft was wrong, not the code
Denys88/rl_games/rl_games/algos_torch/layers.py
code served (permissive licence) · get_code("3e346b9b00ea8169")
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) 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

torch.manual_seed(0)

# The function symlog takes a single parameter x and applies:
# torch.sign(x), torch.log(torch.abs(x) + 1.0)
# So x should be a tensor that supports these operations

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 3 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
symexp 5 other papers
5 later
2301.04104 (2023-01)
Mastering Diverse Domains through World Models
2310.05167 (2023-10)
Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
2403.09859 (2024-03)
MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
and 2 more not named here
symlog 5 other papers
5 later
2301.04104 (2023-01)
Mastering Diverse Domains through World Models
2310.05167 (2023-10)
Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
2403.09859 (2024-03)
MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
and 2 more not named here
rescale_actions 2 other papers
2 later
2410.03441 (2024-10)
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
2502.20390 (2025-02)
INTERMIMIC: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions

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

Recent work has demonstrated the ability of deep reinforcement learning (RL) algorithms to learn complex robotic behaviours in simulation, including in the domain of multi-fingered manipulation. However, such models can be challenging to transfer to the real world due to the gap between simulation and reality. In this paper, we present our techniques to train a) a policy that can perform robust dexterous manipulation on an anthropomorphic robot hand and b) a robust pose estimator suitable for providing reliable real-time information on the state of the object being manipulated. Our policies are trained to adapt to a wide range of conditions in simulation. Consequently, our vision-based policies significantly outperform the best vision policies in the literature on the same reorientation task and are competitive with policies that are given privileged state information via motion capture systems. Our work reaffirms the possibilities of sim-to-real transfer for dexterous manipulation in diverse kinds of hardware and simulator setups, and in our case, with the Allegro Hand and Isaac Gym GPU-based simulation. Furthermore, it opens up possibilities for researchers to achieve such results with commonly-available, affordable robot hands and cameras. Videos of the resulting policy and supplementary information, including experiments and demos, can be found at https://dextreme.org/

For agents

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

get_harvested_code_for_paper("2210.13702")
get_code_for_paper("2210.13702")
have("2210.13702")

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

curl https://syntology.ai/api/ran/2210.13702.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.13702.svg)](https://syntology.ai/paper/2210.13702)

Connect an agent — have() is free.