SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.16255 · ICML · 2024

Uncertainty-Aware Reward-Free Exploration with General Function Approximation

Quanquan Gu, Weitong Zhang, Dongruo Zhou, Junkai Zhang

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 failures 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/2406.16255.json · badge: /api/ran/2406.16255.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
uclaml/gfa-rfe canonical (classifier label)
classifier basis: classifier_2025
6 ran · 2 no recorded run
uclaml/GFA-RFE canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
Actor Ran
ran on a synthesized input · constructed an object; no result was computed
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("419af119bd09b0ac")
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 an instance of its own class, Actor: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
from torch import distributions as pyd
from torch.distributions.utils import _standard_normal

torch.manual_seed(0)

class TruncatedNormal(pyd.Normal):
    def __init__(self, loc, scale, low=-1.0, high=1.0, eps=1e-06):
        super().__init__(loc, scale, validate_args=False)
        self.low = low
        self.high = high
        self.eps = eps

    def _clamp(self, x):
        clamped_x = torch.clamp(x, self.low + self.eps, self.high - self.eps)
        x = x - x.detach() + clamped_x.detach()
        return x

    def sample(self, clip=None, sample_shape=torch.Size()):
        shape = self._extended_shape(sample_shape)
        eps = _standard_normal(shape, dtype=self.loc.dtype, device=self.loc.device)
        eps *= self.scale
        if clip is not None:
            eps = torch.clamp(eps, -clip, clip)
        x = self.loc + eps
        return self._clamp(x)

def weight_init(m):
    """Custom weight init for Conv2D and Linear layers."""
    if isinstance(m, nn.Linear):
        nn.init.orthogonal_(m.weight.data)
        if hasattr(m.bias, 'data'):
            m.bias.data.fill_(0.0)
    elif isinstance(m, nn.Conv2d) or isinstance(m, nn.ConvTranspose2d):
        gain = nn.init.calculate_gain('relu')
        nn.init.orthogonal_(m.weight.data, gain)
        if hasattr(m.bias, 'data'):
            m.bias.data.fill_(0.0)

class Actor(nn.Module):
    def __init__(self, obs_type, obs_dim, action_dim, feature_dim, hidden_dim):
        super().__init__()
        feature_dim = feature_dim if obs_type == 'pixels' else hidden_dim
        self.trunk = nn.Sequential(nn.Linear(obs_dim, feature_dim), nn.LayerNorm(feature_dim), nn.Tanh())
        policy_layers = []
        policy_layers += [nn.Linear(feature_dim, hidden_dim), nn.ReLU(inplace=True)]
        if obs_type == 'pixels':
            policy_layers += [nn.Linear(hidden_dim, hidden_dim), nn.ReLU(inplace=True)]
        policy_layers += [nn.Linear(hidden_dim, action_dim)]
        self.policy = nn.Sequential(*policy_layers)
        self.apply(weight_init)

    def forward(self, obs, std):
        h = self.trunk(obs)
        mu = self.policy(h)
        mu = torch.tanh(mu)
        std = torch.ones_like(mu) * std
        dist = TruncatedNormal(mu, std)
        return dist

ARGS = {
    'obs_type': 'pixels',
    'obs_dim': 10,
    'action_dim': 4,
    'feature_dim': 8,
    'hidden_dim': 6,
}
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 Actor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Actor 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
Critic Ran
ran on a synthesized input · constructed an object; no result was computed
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("790cb19787a27e3c")
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 an instance of its own class, Critic: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import types as _types

torch.manual_seed(0)

def weight_init(m):
    """Custom weight init for Conv2D and Linear layers."""
    if isinstance(m, nn.Linear):
        nn.init.orthogonal_(m.weight.data)
        if hasattr(m.bias, 'data'):
            m.bias.data.fill_(0.0)
    elif isinstance(m, nn.Conv2d) or isinstance(m, nn.ConvTranspose2d):
        gain = nn.init.calculate_gain('relu')
        nn.init.orthogonal_(m.weight.data, gain)
        if hasattr(m.bias, 'data'):
            m.bias.data.fill_(0.0)

utils = _types.SimpleNamespace(**{'weight_init': weight_init})

ARGS = {
    'obs_type': 'state',
    'obs_dim': 4,
    'action_dim': 3,
    'feature_dim': 5,
    'hidden_dim': 6
}
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 Critic — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Critic 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
Encoder Ran
ran on a synthesized input · constructed an object; no result was computed
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("2e578a8124e51723")
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 an instance of its own class, Encoder: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import types as _types

torch.manual_seed(0)

def weight_init(m):
    """Custom weight init for Conv2D and Linear layers."""
    if isinstance(m, nn.Linear):
        nn.init.orthogonal_(m.weight.data)
        if hasattr(m.bias, 'data'):
            m.bias.data.fill_(0.0)
    elif isinstance(m, nn.Conv2d) or isinstance(m, nn.ConvTranspose2d):
        gain = nn.init.calculate_gain('relu')
        nn.init.orthogonal_(m.weight.data, gain)
        if hasattr(m.bias, 'data'):
            m.bias.data.fill_(0.0)

utils = _types.SimpleNamespace(**{'weight_init': weight_init})

ARGS = {
    'obs_shape': (3, 84, 84)
}
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 Encoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Encoder 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
RandomShiftsAug Ran
ran on a synthesized input · constructed an object; no result was computed
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("5aee04fb3686517a")
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 an instance of its own class, RandomShiftsAug: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pad': 2
}
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 RandomShiftsAug — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RandomShiftsAug 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
VectorizedCritics Ran
ran on a synthesized input · constructed an object; no result was computed
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("a8a8005cfb1d6a98")
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 an instance of its own class, VectorizedCritics: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

class VectorizedLinear(nn.Module):

    def __init__(self, in_features: int, out_features: int, ensemble_size: int):
        super().__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.ensemble_size = ensemble_size
        self.weight = nn.Parameter(torch.empty(ensemble_size, in_features, out_features))
        self.bias = nn.Parameter(torch.empty(ensemble_size, 1, out_features))
        self.reset_parameters()

    def reset_parameters(self):
        for layer in range(self.ensemble_size):
            nn.init.kaiming_uniform_(self.weight[layer], a=math.sqrt(5))
        fan_in, _ = nn.init._calculate_fan_in_and_fan_out(self.weight[0])
        bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0
        nn.init.uniform_(self.bias, -bound, bound)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        return x @ self.weight + self.bias

class VectorizedCritics(nn.Module):

    def __init__(self, obs_type, obs_dim, action_dim, feature_dim, hidden_dim, ensemble_size):
        super().__init__()
        self.obs_type = obs_type
        if obs_type == 'pixels':
            self.trunk = nn.Sequential(VectorizedLinear(obs_dim, feature_dim, ensemble_size), nn.LayerNorm(feature_dim), nn.Tanh())
            self.Qs = nn.Sequential(VectorizedLinear(feature_dim + action_dim, hidden_dim, ensemble_size), nn.ReLU(inplace=True), VectorizedLinear(hidden_dim, hidden_dim, ensemble_size), nn.ReLU(inplace=True), VectorizedLinear(hidden_dim, 1, ensemble_size))
        else:
            self.trunk = nn.Sequential(VectorizedLinear(obs_dim + action_dim, hidden_dim, ensemble_size), nn.LayerNorm(hidden_dim), nn.Tanh())
            self.Qs = nn.Sequential(VectorizedLinear(hidden_dim, hidden_dim, ensemble_size), nn.ReLU(inplace=True), VectorizedLinear(hidden_dim, 1, ensemble_size))

    def forward(self, obs, action):
        inpt = obs if self.obs_type == 'pixels' else torch.cat([obs, action], dim=-1)
        h = self.trunk(inpt)
        h = torch.cat([h, action], dim=-1) if self.obs_type == 'pixels' else h
        Qs = self.Qs(h)
        return Qs

ARGS = {
    'obs_type': 'pixels',
    'obs_dim': 4,
    'action_dim': 3,
    'feature_dim': 5,
    'hidden_dim': 6,
    'ensemble_size': 2
}
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 VectorizedCritics — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a VectorizedCritics 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
episode_len Ran
ran, honoured the contract we drafted
uclaml/GFA-RFE/replay_buffer.py
code served (permissive licence) · get_code("9f840a22d31a89bc")
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 int, ndim 0, dtype family int, 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

torch.manual_seed(0)

# The function accesses episode.values() and calls .shape[0] on the result
# So episode should be a dict where values are tensors (or array-like with shape)
# The function returns shape[0] - 1, so we need at least 1 element in dimension 0

episode = {
    "observations": torch.randn(5, 4),
    "actions": torch.randn(5, 3),
    "rewards": torch.randn(5, 2),
}

ARGS = {
    "episode": episode
}
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 int, ndim 0, dtype family int, 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
grad_norm Ran
ran, honoured the contract we drafted
uclaml/GFA-RFE/utils.py
code served (permissive licence) · get_code("2478bb95b38ef24f")
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)

# Create a simple model with parameters that have gradients
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create some dummy input and target
x = torch.randn(2, 4)
target = torch.randn(2, 2)

# Forward pass to generate gradients
output = model(x)
loss = torch.nn.functional.mse_loss(output, target)
loss.backward()

# Extract parameters with gradients
params = [p for p in model.parameters() if p.grad is not None]

ARGS = {
    "params": params,
    "norm_type": 2.0
}
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 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
load_episode Ran
ran; our contract draft was wrong, not the code
uclaml/GFA-RFE/replay_buffer.py
code served (permissive licence) · get_code("184876e5f4ab6562")
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 dict. 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
from pathlib import Path
import tempfile
import os

# Create a temporary file to serve as the episode file
temp_dir = tempfile.mkdtemp()
temp_file_path = Path(temp_dir) / "episode.npz"

# Create a sample episode dictionary with numpy arrays
episode_data = {
    'observations': np.random.rand(5, 4).astype(np.float32),
    'actions': np.random.randint(0, 3, size=(5,)).astype(np.int32),
    'rewards': np.random.rand(5).astype(np.float32),
    'dones': np.random.randint(0, 2, size=(5,)).astype(bool),
}

# Save as npz file
np.savez(temp_file_path, **episode_data)

# Define ARGS with the file path
ARGS = {
    'fn': temp_file_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
make_replay_loader Ran
ran; our contract draft was wrong, not the code
uclaml/GFA-RFE/replay_buffer.py
code served (permissive licence) · get_code("e4f44028e6834d07")
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 DataLoader. 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
import random
from pathlib import Path
from unittest.mock import Mock, MagicMock
import tempfile

torch.manual_seed(0)
np.random.seed(0)
random.seed(0)

# Create a temporary directory for storage
temp_dir = tempfile.TemporaryDirectory()
replay_dir = Path(temp_dir.name)

# Create mock storage object with required attributes
storage = Mock()
storage._replay_dir = replay_dir

# Create mock meta specs
meta_spec = Mock()
meta_spec.name = 'meta_field'
storage._meta_specs = [meta_spec]

# Create a sample episode file for offline mode
episode_data = {
    'observation': np.random.randn(10, 4).astype(np.float32),
    'action': np.random.randn(10, 3).astype(np.float32),
    'reward': np.random.randn(10, 1).astype(np.float32),
    'discount': np.ones((10, 1), dtype=np.float32),
    'meta_field': np.random.randn(10, 2).astype(np.float32),
}

# Save episode to disk
episode_path = replay_dir / 'episode_0_8.npz'
np.savez(episode_path, **episode_data)

ARGS = {
    'storage': storage,
    'max_size': 1000,
    'batch_size': 2,
    'num_workers': 1,
    'save_snapshot': False,
    'nstep': 3,
    'discount': 0.99,
    'is_offline': True,
    'num_episodes': 1,
}
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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
param_norm Ran
ran, honoured the contract we drafted
uclaml/GFA-RFE/utils.py
code served (permissive licence) · get_code("8708aaca52006e47")
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)

# Create a small neural network with a few parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Extract parameters from the model
params = list(model.parameters())

# Define ARGS dict with all parameters
ARGS = {
    'params': params,
    'norm_type': 2.0
}
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 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
schedule Ran
ran, honoured the contract we drafted
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("ae234269debed3f4")
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 re
import numpy as np

# Test case 1: simple float string
ARGS = {
    "schdl": "0.5",
    "step": 10
}
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 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
to_torch Ran
ran; our contract draft was wrong, not the code
uclaml/GFA-RFE/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from premiertaco/premier-taco, is pointer only (licence: NONE) · get_code("6244e9922f4e0610")
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 premiertaco/premier-taco, 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.

D2Agent Not yet run
unverified (harvested, no recorded run)
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("dbe65af46016bc97")
How it ran

no invocation recorded.

DDPGAgent Not yet run
unverified (harvested, no recorded run)
uclaml/gfa-rfe/agent/dsquare.py
code served (permissive licence) · get_code("4c262c61dad0f383")
How it ran

no invocation recorded.

make_agent Not yet run
unverified (harvested, no recorded run)
uclaml/GFA-RFE/offline.py
code served (permissive licence) · get_code("2a76dfe317adeb03")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 1 the same month, 5 later) and 4 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
to_torch
brick of this paper's assembly: helper
23 other papers
22 dated earlier, 1 later · 7 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
and 20 more not named here
schedule
brick of this paper's assembly: helper
17 other papers
16 dated earlier, 1 later · 7 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
and 14 more not named here
episode_len 12 other papers
10 dated earlier, 2 later
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2211.12740 (2022-11)
Masked Autoencoding for Scalable and Generalizable Decision Making
2302.00965 (2023-02)
Visual Imitation Learning with Patch Rewards
and 9 more not named here
load_episode 10 other papers
8 dated earlier, 2 later
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2302.00965 (2023-02)
Visual Imitation Learning with Patch Rewards
2303.01497 (2023-03)
Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations
and 7 more not named here
make_agent 9 other papers
7 dated earlier, 1 the same month, 1 later
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2110.15191 (2021-10)
URLB: Unsupervised Reinforcement Learning Benchmark
2202.00161 (2022-02)
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
and 6 more not named here
Encoder
brick of this paper's assembly: helper
5 other papers
5 dated earlier · 2 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
2210.10765 (2022-10)
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
and 2 more not named here
grad_norm 4 other papers
4 dated earlier
2211.12740 (2022-11)
Masked Autoencoding for Scalable and Generalizable Decision Making
2305.04477 (2023-05)
Behavior Contrastive Learning for Unsupervised Skill Discovery
2405.14073 (2024-05)
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
and 1 more not named here
param_norm 3 other papers
3 dated earlier
2305.04477 (2023-05)
Behavior Contrastive Learning for Unsupervised Skill Discovery
2405.14073 (2024-05)
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
2405.16030 (2024-05)
Constrained Ensemble Exploration for Unsupervised Skill Discovery
Actor
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
Critic
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
RandomShiftsAug
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training

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

Mastering multiple tasks through exploration and learning in an environment poses a significant challenge in reinforcement learning (RL). Unsupervised RL has been introduced to address this challenge by training policies with intrinsic rewards rather than extrinsic rewards. However, current intrinsic reward designs and unsupervised RL algorithms often overlook the heterogeneous nature of collected samples, thereby diminishing their sample efficiency. To overcome this limitation, in this paper, we propose a reward-free RL algorithm called GFA-RFE. The key idea behind our algorithm is an uncertaintyaware intrinsic reward for exploring the environment and an uncertainty-weighted learning process to handle heterogeneous uncertainty in different samples. Theoretically, we show that in order to find an ϵ-optimal policy, GFA-RFE needs to collect O(H 2 log N F (ϵ) dim(F)/ϵ 2 ) number of episodes, where F is the value function class with covering number N F (ϵ) and generalized eluder dimension dim(F). Such a result outperforms all existing reward-free RL algorithms. We further implement and evaluate GFA-RFE across various domains and tasks in the DeepMind Control Suite. Experiment results show that GFA-RFE outperforms or is comparable to the performance of state-of-the-art unsupervised RL algorithms.

For agents

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

get_harvested_code_for_paper("2406.16255")
get_code_for_paper("2406.16255")
have("2406.16255")

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

curl https://syntology.ai/api/ran/2406.16255.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.16255.svg)](https://syntology.ai/paper/2406.16255)

Connect an agent — have() is free.