SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02722 · 2026

Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion

Amy Zhang, Tal Daniel, Aviv Tamar, George Konidaris, Dan Haramati, Carl Qi

arXiv · PDF · Open in the Atlas

Code that ran

21 of 31 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 10 failures of our instrument; 10 no recorded run), measured 2026-11-22; 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/2602.02722.json · badge: /api/ran/2602.02722.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
DanHrmti/ECRL canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
DanHrmti/HECRL community
Papers with Code archive
11 ran · 5 no recorded run
carl-qi/EC-Diffuser community
Papers with Code archive
3 ran · 3 no recorded run
FunctionStatusWhere it lives
EntityAttention Ran
ran on a synthesized input · constructed an object; no result was computed
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("09f1831060c9ac79")
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, EntityAttention: 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
import torch.nn.functional as F

torch.manual_seed(0)

class EntityAttention(nn.Module):
    """
    Entity-based multi-head masked self-attention layer.

    This module implements multi-head attention over entity representations.
    It supports three types of attention:
      - 'self': standard self-attention.
      - 'cross': attention over a conditioning input `c`.
      - 'hybrid': concatenates self and conditioning inputs.
    
    Args:
        n_embed (int): Dimensionality of the input embeddings.
        n_head (int): Number of attention heads.
        attn_pdrop (float): Dropout probability on attention weights.
        resid_pdrop (float): Dropout probability on the output projection.
        linear_bias (bool): If True, include bias terms in the linear projections.
        att_type (str): Type of attention: 'self', 'cross', or 'hybrid'.
    """

    def __init__(self, n_embed, n_head, attn_pdrop=0.1, resid_pdrop=0.1, linear_bias=False, att_type='self'):
        super().__init__()
        assert n_embed % n_head == 0
        assert att_type in ['hybrid', 'cross', 'self']
        self.att_type = att_type
        self.key = nn.Linear(n_embed, n_embed, bias=linear_bias)
        self.query = nn.Linear(n_embed, n_embed, bias=linear_bias)
        self.value = nn.Linear(n_embed, n_embed, bias=linear_bias)
        self.attn_drop = nn.Dropout(attn_pdrop)
        self.resid_drop = nn.Dropout(resid_pdrop)
        self.proj = nn.Linear(n_embed, n_embed, bias=linear_bias)
        self.n_head = n_head

    def forward(self, x, c=None):
        B, N, T, C = x.size()
        query_input = x
        if self.att_type == 'hybrid':
            key_value_input = torch.cat([x, c], dim=1)
            key_value_N = key_value_input.shape[1]
            key_value_T = key_value_input.shape[2]
        elif self.att_type == 'cross':
            key_value_input = c
            key_value_N = key_value_input.shape[1]
            key_value_T = key_value_input.shape[2]
        else:
            key_value_input = x
            key_value_N = N
            key_value_T = T
        k = self.key(key_value_input).view(B, key_value_N * key_value_T, self.n_head, C // self.n_head).transpose(1, 2)
        q = self.query(query_input).view(B, N * T, self.n_head, C // self.n_head).transpose(1, 2)
        v = self.value(key_value_input).view(B, key_value_N * key_value_T, self.n_head, C // self.n_head).transpose(1, 2)
        att = q @ k.transpose(-2, -1) * (1.0 / math.sqrt(k.size(-1)))
        att = F.softmax(att, dim=-1)
        att = self.attn_drop(att)
        y = att @ v
        y = y.transpose(1, 2).contiguous().view(B, N * T, C)
        y = self.resid_drop(self.proj(y))
        y = y.view(B, N, T, -1)
        return y

# Setup arguments for EntityAttention.__init__
ARGS = {
    'n_embed': 4,
    'n_head': 2,
    'attn_pdrop': 0.1,
    'resid_pdrop': 0.1,
    'linear_bias': False,
    'att_type': 'self'
}
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 EntityAttention — 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 EntityAttention 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
FinalLayer Ran
ran on a synthesized input
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("eff3741649fc49e6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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

def modulate(x, shift, scale):
    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)

class FinalLayer(nn.Module):
    """
    Final adaptive modulation layer.
    """

    def __init__(self, dim):
        super().__init__()
        self.ln_final = nn.LayerNorm(dim, elementwise_affine=False, eps=1e-06)
        self.gamma = nn.Linear(dim, dim)
        self.beta = nn.Linear(dim, dim)
        nn.init.zeros_(self.gamma.weight)
        nn.init.zeros_(self.beta.weight)
        nn.init.zeros_(self.gamma.bias)
        nn.init.zeros_(self.beta.bias)

    def forward(self, x, c):
        scale = self.gamma(c)
        shift = self.beta(c)
        x = modulate(self.ln_final(x), shift, scale)
        return x

INIT_ARGS = {
    'dim': 6
}

ARGS = {
    'x': torch.randn(2, 5, 6),
    'c': torch.randn(2, 6)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
FinalLayer Ran
ran on a synthesized input · constructed an object; no result was computed
carl-qi/EC-Diffuser/diffuser/diffuser/models/transformer_modules.py
code served (permissive licence) · get_code("f7534870f9202f83")
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, FinalLayer: 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)

# Define the FinalLayer module
class FinalLayer(nn.Module):
    """
    Final adaptive modulation layer.
    """

    def __init__(self, dim):
        super().__init__()
        self.ln_final = nn.LayerNorm(dim, elementwise_affine=False, eps=1e-06)
        self.gamma = nn.Linear(dim, dim)
        self.beta = nn.Linear(dim, dim)
        nn.init.zeros_(self.gamma.weight)
        nn.init.zeros_(self.gamma.bias)
        nn.init.zeros_(self.beta.weight)
        nn.init.zeros_(self.beta.bias)

    def forward(self, x, c):
        scale = self.gamma(c)
        shift = self.beta(c)
        x = modulate(self.ln_final(x), shift, scale)
        return x


def modulate(x, shift, scale):
    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)


# Create test data
dim = 4
batch_size = 2

# Input tensor x: (batch_size, seq_len, dim)
x = torch.randn(batch_size, 3, dim)

# Conditioning tensor c: (batch_size, dim)
c = torch.randn(batch_size, dim)

# Create FinalLayer module instance
final_layer = FinalLayer(dim)

# Define ARGS dict
ARGS = {
    "dim": dim,
}
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 FinalLayer — 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 FinalLayer 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
GaussianDiffusion Ran
ran on a synthesized input · constructed an object; no result was computed
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("54539835cf34d475")
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, GaussianDiffusion: 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 numpy as np

torch.manual_seed(0)

class DummyModel(nn.Module):
    """Minimal model that satisfies how GaussianDiffusion uses it."""
    def __init__(self, transition_dim):
        super().__init__()
        self.transition_dim = transition_dim
        self.linear = nn.Linear(transition_dim + 1, transition_dim)
    
    def forward(self, x, cond, t):
        # x shape: (batch, horizon, transition_dim)
        # cond shape: (batch, horizon, transition_dim) or similar
        # t shape: (batch,)
        batch_size, horizon, dim = x.shape
        # Flatten and process
        x_flat = x.reshape(batch_size, -1)
        # Add time as a feature
        t_expanded = t.float().unsqueeze(1)
        combined = torch.cat([x_flat, t_expanded], dim=1)
        # Reshape output back
        out = self.linear(combined)
        return out.reshape(batch_size, horizon, dim)

# Set up parameters for GaussianDiffusion
horizon = 4
observation_dim = 3
action_dim = 2
n_timesteps = 10

model = DummyModel(transition_dim=observation_dim + action_dim)

ARGS = {
    'model': model,
    'horizon': horizon,
    'observation_dim': observation_dim,
    'action_dim': action_dim,
    'n_timesteps': n_timesteps,
    'loss_type': 'l1',
    'clip_denoised': False,
    'predict_epsilon': True,
}
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 GaussianDiffusion — 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 GaussianDiffusion 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
GoalConditionedSampler Ran
ran on a synthesized input · constructed an object; no result was computed
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("631ebce8b5618a76")
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, GoalConditionedSampler: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 einops

torch.manual_seed(0)

# Create a minimal diffusion model that satisfies the interface
class MinimalDiffusionModel(nn.Module):
    def __init__(self, action_dim=4, obs_dim=3):
        super().__init__()
        self.action_dim = action_dim
        self.obs_dim = obs_dim
        self.linear = nn.Linear(action_dim + obs_dim, action_dim + obs_dim)
    
    def forward(self, conditions, sort_by_value=False, **kwargs):
        # Return a mock output with trajectories attribute
        # conditions is a dict, we need to extract batch_size and sequence_length
        batch_size = next(iter(conditions.values())).shape[0]
        
        # Create mock trajectories: [batch_size, seq_len, action_dim + obs_dim]
        trajectories = torch.randn(batch_size, 2, self.action_dim + self.obs_dim)
        
        class MockSamples:
            pass
        
        samples = MockSamples()
        samples.trajectories = trajectories
        return samples
    
    def parameters(self):
        return super().parameters()

# Create a minimal normalizer
class MinimalNormalizer:
    def __init__(self):
        pass
    
    def normalize(self, x):
        return x
    
    def unnormalize(self, x):
        return x

# Create minimal preprocess functions (list/dict of callables)
preprocess_fns = {
    'obs': lambda x: x,
    'action': lambda x: x,
}

# Instantiate components
action_dim = 4
obs_dim = 3
diffusion_model = MinimalDiffusionModel(action_dim=action_dim, obs_dim=obs_dim)
normalizer = MinimalNormalizer()

# Define ARGS with all required parameters for GoalConditionedSampler.__init__
ARGS = {
    'diffusion_model': diffusion_model,
    'normalizer': normalizer,
    'preprocess_fns': preprocess_fns,
    'sample_kwargs': {'num_steps': 10}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GoalConditionedSampler — 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 GoalConditionedSampler 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
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("35583be7932ff902")
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, MLP: 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 = {
    "n_embed": 256,
    "resid_pdrop": 0.1,
    "hidden_dim_multiplier": 4,
    "activation": "gelu",
}
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 MLP — 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 MLP 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
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
carl-qi/EC-Diffuser/diffuser/diffuser/models/transformer_modules.py
code served (permissive licence) · get_code("d95157530021729f")
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, MLP: 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 = {
    'n_embed': 64,
    'resid_pdrop': 0.1,
    'hidden_dim_multiplier': 4,
    'activation': 'gelu'
}
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 MLP — 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 MLP 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
SimpleRelativePositionalBias Ran
ran on a synthesized input · constructed an object; no result was computed
carl-qi/EC-Diffuser/diffuser/diffuser/models/transformer_modules.py
code served (permissive licence) · get_code("1d4bb5bf017a860c")
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, SimpleRelativePositionalBias: 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    "max_positions": 64,
    "num_heads": 8,
    "max_particles": 16,
    "layer_norm": True,
}
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 SimpleRelativePositionalBias — 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 SimpleRelativePositionalBias 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
SinusoidalPosEmb Ran
ran on a synthesized input · constructed an object; no result was computed
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("3f9e9512b765d426")
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, SinusoidalPosEmb: 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)

# The forward method expects x to be a tensor of shape (batch_size,)
# It will be used as: x[:, None] * emb[None, :]
# So x should be a 1D tensor (batch dimension)
x = torch.tensor([1.0, 2.0])

# The __init__ method expects dim to be an integer
# It's used as: half_dim = self.dim // 2
# and then torch.arange(half_dim, device=device)
dim = 4

ARGS = {
    'dim': dim,
}
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 SinusoidalPosEmb — 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 SinusoidalPosEmb 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
apply_conditioning Ran
ran; our contract draft was wrong, not the code
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("b3d593fb33f79ac5")
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 3, dtype family float, shape (2, 5, 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 as nn

torch.manual_seed(0)

# x: tensor that will be indexed and have values assigned
# The function indexes x[:, t, action_dim:] where t comes from conditions.keys()
# and assigns val.clone() to it
# So x needs shape (batch_size, time_steps, feature_dim)
# with feature_dim > action_dim
batch_size = 2
time_steps = 5
action_dim = 2
feature_dim = 4  # must be > action_dim

x = torch.randn(batch_size, time_steps, feature_dim)

# conditions: dict mapping timestep t to a tensor val
# The function does x[:, t, action_dim:] = val.clone()
# So val should have shape (batch_size, feature_dim - action_dim)
condition_shape = (batch_size, feature_dim - action_dim)
conditions = {
    1: torch.randn(condition_shape),
    3: torch.randn(condition_shape),
}

ARGS = {
    "x": x,
    "conditions": conditions,
    "action_dim": action_dim,
}
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 3, dtype family float, shape (2, 5, 4) — shape (2, 5, 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
axisangle2quat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DanHrmti/ECRL/isaac_panda_push_env.py
code served (permissive licence) · get_code("c6779ef568a575ea")
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 3, dtype family float, shape (2, 4, 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)

# Create a small axis-angle tensor with shape (..., 3)
# Using batch size 2 with 4 different shapes to test broadcasting
vec = torch.randn(2, 4, 3)

# eps parameter - default stability threshold
eps = 1e-06

ARGS = {
    "vec": vec,
    "eps": eps,
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
conv2d Ran
ran; our contract draft was wrong, not the code
DanHrmti/ECRL/slot_attention/slate_model.py
code served (permissive licence) · get_code("9330641b45f958fd")
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 Conv2d. 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 = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'dilation': 1,
    'groups': 1,
    'bias': True,
    'padding_mode': 'zeros',
    'weight_init': 'xavier'
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
convert_obs_to_dlp_rep Ran
ran; our contract draft was wrong, not the code
DanHrmti/ECRL/chamfer_reward.py
code served (permissive licence) · get_code("62001b2163460d68")
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 3, dtype family float, shape (2, 3, 11) 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)

class MockDLPModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(12, 20)
    
    def encode_all(self, normalized_obs, deterministic=True):
        batch_size = normalized_obs.shape[0]
        z = torch.randn(batch_size, 2)
        mu_scale = torch.randn(batch_size, 2)
        mu_depth = torch.randn(batch_size, 1)
        mu_features = torch.randn(batch_size, 5)
        obj_on = torch.randint(0, 2, (batch_size,)).float()
        
        return {
            'z': z,
            'mu_scale': mu_scale,
            'mu_depth': mu_depth,
            'mu_features': mu_features,
            'obj_on': obj_on
        }

obs = torch.randint(0, 256, (2, 3, 4, 4), dtype=torch.uint8)
dlp_model = MockDLPModel()

ARGS = {
    'obs': obs,
    'dlp_model': dlp_model
}
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 3, dtype family float, shape (2, 3, 11) — shape (2, 3, 11) 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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("b6113e0f43155a33")
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 (10,) 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
import torch

torch.manual_seed(0)

ARGS = {
    "timesteps": 10,
    "s": 0.008,
    "dtype": torch.float32,
}
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 (10,) — shape (10,) 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
default_sample_fn Ran
ran; our contract draft was wrong, not the code
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("896418fd494c4d3d")
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 torch.nn as nn

torch.manual_seed(0)

class MockDiffusionModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def p_mean_variance(self, x, cond, t):
        # x: [batch, 4]
        # Returns: model_mean, model_variance, model_log_variance
        batch_size = x.shape[0]
        model_mean = self.linear(x)
        model_variance = torch.ones(batch_size, 4)
        model_log_variance = torch.zeros(batch_size, 4)
        return model_mean, model_variance, model_log_variance

model = MockDiffusionModel()

x = torch.randn(2, 4)
cond = torch.randn(2, 3)
t = torch.tensor([1, 0])

ARGS = {
    "model": model,
    "x": x,
    "cond": cond,
    "t": t,
}
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
extract_dlp_features Ran
ran; our contract draft was wrong, not the code
DanHrmti/ECRL/chamfer_reward.py
code served (permissive licence) · get_code("03234d185899f504")
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 3, dtype family float, shape (2, 2, 19) 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)

class MockDLPModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(12, 1)
    
    def encode_all(self, normalized_obs, deterministic=False):
        batch_size = normalized_obs.shape[0]
        output = {
            'z': torch.randn(batch_size, 2, 4),
            'mu_scale': torch.randn(batch_size, 2, 3),
            'mu_depth': torch.randn(batch_size, 2, 5),
            'mu_features': torch.randn(batch_size, 2, 6),
            'obj_on': torch.randn(batch_size, 2)
        }
        return output

dlp_model = MockDLPModel()
obs = torch.randint(0, 256, (2, 12), dtype=torch.uint8)

ARGS = {
    'obs': obs,
    'dlp_model': dlp_model
}
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 3, dtype family float, shape (2, 2, 19) — shape (2, 2, 19) 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
extract_dlp_features Ran
ran; our contract draft was wrong, not the code
DanHrmti/ECRL/latent_classifier.py
code served (permissive licence) · get_code("62186577f208bf25")
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 torch.nn as nn

torch.manual_seed(0)

class MockDLPModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(12, 32)
    
    def encode_all(self, observations, deterministic=False):
        batch_size = observations.shape[0]
        z = torch.randn(batch_size, 2, 2)
        mu_scale = torch.randn(batch_size, 2, 3)
        mu_depth = torch.randn(batch_size, 2, 4)
        mu_features = torch.randn(batch_size, 2, 5)
        obj_on = torch.randn(batch_size, 2)
        cropped_objects = torch.randn(batch_size, 2, 3, 8, 8)
        
        return {
            'z': z,
            'mu_scale': mu_scale,
            'mu_depth': mu_depth,
            'mu_features': mu_features,
            'obj_on': obj_on,
            'cropped_objects': cropped_objects
        }

dlp_model = MockDLPModel()
obs = torch.randint(0, 256, (2, 3, 32, 32), dtype=torch.uint8)

ARGS = {
    'obs': obs,
    'dlp_model': dlp_model
}
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
gumbel_softmax Ran
ran; our contract draft was wrong, not the code
DanHrmti/ECRL/slot_attention/slate_model.py
code served (permissive licence) · get_code("94c911439007d22c")
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 logits tensor with shape (batch=2, classes=4)
logits = torch.randn(2, 4)

# Define arguments for gumbel_softmax
ARGS = {
    "logits": logits,
    "tau": 1.0,
    "hard": False,
    "dim": -1
}
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
quat2axisangle Ran
ran; our contract draft was wrong, not the code
DanHrmti/ECRL/isaac_panda_push_env.py
code served (permissive licence) · get_code("0a0911522ce533d0")
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, 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 torch

torch.manual_seed(0)

# Create a small quaternion tensor with shape (2, 4)
# representing 2 quaternions in (x, y, z, w) format
quat = torch.tensor([
    [0.0, 0.0, 0.7071068, 0.7071068],  # 90 degree rotation around z-axis
    [0.0, 0.0, 0.0, 1.0]                # identity quaternion
], dtype=torch.float32)

ARGS = {
    "quat": quat
}
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, 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
sort_by_values Ran
ran, honoured the contract we drafted
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("c409be426eec3eec")
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

torch.manual_seed(0)

# Create small tensors for testing
x = torch.randn(2, 4)  # batch_size=2, feature_dim=4
values = torch.tensor([3.5, 1.2])  # 2 values corresponding to batch items

ARGS = {
    "x": x,
    "values": values,
}
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
to_torch Ran
ran; our contract draft was wrong, not the code
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("9d23c8e40238297e")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# Test with various input types
x_list = [1.0, 2.0, 3.0, 4.0]
x_tensor = torch.randn(2, 4)
x_dict = {
    'a': [1.0, 2.0, 3.0],
    'b': torch.randn(2, 4),
    'c': {'nested': [5.0, 6.0]}
}

ARGS = {
    'x': x_dict,
    'dtype': torch.float32,
    'device': 'cpu'
}
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 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
AdaLNEITBlock Not yet run
unverified (harvested, no recorded run)
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("63b4f79f55f7aee8")
How it ran

no invocation recorded.

AdaLNEntityTransformer Not yet run
unverified (harvested, no recorded run)
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("f474464406bc42e7")
How it ran

no invocation recorded.

AdaLNPINTBlock Not yet run
unverified (harvested, no recorded run)
carl-qi/EC-Diffuser/diffuser/diffuser/models/transformer_modules.py
code served (permissive licence) · get_code("c129051ef1ab4cb6")
How it ran

no invocation recorded.

AdaLNParticleTransformer Not yet run
unverified (harvested, no recorded run)
carl-qi/EC-Diffuser/diffuser/diffuser/models/transformer_modules.py
code served (permissive licence) · get_code("8196622b45ac426b")
How it ran

no invocation recorded.

CausalParticleAttention Not yet run
unverified (harvested, no recorded run)
carl-qi/EC-Diffuser/diffuser/diffuser/models/transformer_modules.py
code served (permissive licence) · get_code("3a9859a10e10a315")
How it ran

no invocation recorded.

SubgoalDiffuser Not yet run
unverified (harvested, no recorded run)
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("dd04ddf6e3a6b579")
How it ran

no invocation recorded.

TransformerDiffuser Not yet run
unverified (harvested, no recorded run)
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("1e098df88752131f")
How it ran

no invocation recorded.

apply_dict Not yet run
unverified (harvested, no recorded run)
DanHrmti/HECRL/agents/diffuser/subgoal_diffuser.py
code served (permissive licence) · get_code("bf97061c5f8a7aa2")
How it ran

no invocation recorded.

get_dlp_rep Not yet run
unverified (harvested, no recorded run)
DanHrmti/ECRL/chamfer_reward.py
code served (permissive licence) · get_code("649850da42fe3886")
How it ran

no invocation recorded.

get_dlp_rep Not yet run
unverified (harvested, no recorded run)
DanHrmti/ECRL/latent_classifier.py
code served (permissive licence) · get_code("3219c7505517e845")
How it ran

no invocation recorded.

Also present in other papers' code

Of 31 samples lifted from this paper's linked repositories, 31 carry a function identity and 0 do not. Of the 29 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 1 the same month, 3 later) and 15 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
cosine_beta_schedule
brick of this paper's assembly: helper
20 other papers
19 dated earlier, 1 later · 8 only as an assembly brick
2208.06193 (2022-08)
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
2210.15629 (2022-10)
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
2303.14676 (2023-03)
PDPP: Projected Diffusion for Procedure Planning in Instructional Videos
and 17 more not named here
SinusoidalPosEmb
brick of this paper's assembly: helper
19 other papers
16 dated earlier, 1 the same month, 2 later · 13 only as an assembly brick
2208.06193 (2022-08)
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
2309.03729 (2023-09)
Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption
2310.05333 (2023-10)
DiffCPS: Diffusion-based Constrained Policy Search for Offline Reinforcement Learning
and 16 more not named here
apply_conditioning
brick of this paper's assembly: helper
9 other papers
8 dated earlier, 1 later · 2 only as an assembly brick
2210.15629 (2022-10)
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
2305.18459 (2023-05)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
2405.04235 (2024-05)
LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning
and 6 more not named here
gumbel_softmax 5 other papers
5 dated earlier
2110.11405 (2021-10)
Illiterate DALL-E Learns to Compose
2205.14065 (2022-05)
Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos
2211.01177 (2022-11)
Neural Systematic Binder
and 2 more not named here
sort_by_values
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 1 only as an assembly brick
2305.18459 (2023-05)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
2312.08533 (2023-12)
World Models via Policy-Guided Trajectory Diffusion
2402.14407 (2024-02)
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
and 1 more not named here
axisangle2quat 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
conv2d 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
convert_obs_to_dlp_rep 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
default_sample_fn
brick of this paper's assembly: sampler
1 other paper
1 dated earlier · 1 only as an assembly brick
2305.18459 (2023-05)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
extract_dlp_features 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
extract_dlp_features 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
get_dlp_rep 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
get_dlp_rep 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
quat2axisangle 1 other paper
1 dated earlier
2404.01220 (2024-04)
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

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 propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multiple entities. Achieving long-horizon goals in complex environments remains a core challenge in Reinforcement Learning (RL). Domains with multiple entities are particularly difficult due to their combinatorial complexity. GCRL facilitates generalization across goals and the use of subgoal structure, but struggles with high-dimensional observations and combinatorial state-spaces, especially under sparse reward. We employ a two-level hierarchy composed of a value-based GCRL agent and a factored subgoal-generating conditional diffusion model. The RL agent and subgoal generator are trained independently and composed post hoc through selective subgoal generation based on the value function, making the approach modular and compatible with existing GCRL algorithms. We introduce new variations to benchmark tasks that highlight the challenges of multi-entity domains, and show that our method consistently boosts performance of the underlying RL agent on image-based long-horizon tasks with sparse rewards, achieving over 150% higher success rates on the hardest task in our suite and generalizing to increasing horizons and numbers of entities. Rollout videos are provided at: https://sites.google.com/view/hecrl.

For agents

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

get_harvested_code_for_paper("2602.02722")
get_code_for_paper("2602.02722")
have("2602.02722")

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

curl https://syntology.ai/api/ran/2602.02722.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02722.svg)](https://syntology.ai/paper/2602.02722)

Connect an agent — have() is free.