SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09750 · ICML · 2024

Exploration and Anti-Exploration with Distributional Random Network Distillation

Xiu Li, Kai Yang, Jiafei Lyu, Jian Tao

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.09750.json · badge: /api/ran/2401.09750.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
yk7333/DRND canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
yk7333/drnd canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
DRNDModel Ran
ran on a synthesized input · constructed an object; no result was computed
yk7333/drnd/online/model.py
code served (permissive licence) · get_code("5866b6a1c530319d")
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, DRNDModel: 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 numpy as np

torch.manual_seed(0)

ARGS = {
    'input_size': 84,
    'output_size': 18,
    'num': 3,
    'device': 'cpu'
}
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 DRNDModel — 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 DRNDModel 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
global_grad_norm_ Ran
ran, honoured the contract we drafted
yk7333/DRND/online/utils.py
code served (permissive licence) · get_code("99ed96c42bb4247a")
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
from torch import inf

torch.manual_seed(0)

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

model = SimpleModel()

# Create some dummy data and compute gradients
x = torch.randn(2, 4)
y = torch.randn(2, 2)

output = model(x)
loss = torch.nn.functional.mse_loss(output, y)
loss.backward()

# Collect parameters with gradients
parameters = list(model.parameters())

ARGS = {
    "parameters": parameters,
    "norm_type": 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 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
softmax Ran
ran, honoured the contract we drafted
yk7333/DRND/online/utils.py
code served (permissive licence) · get_code("011537d0bea7fe09")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 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 numpy as np

# Create a small 2D numpy array (batch_size=2, features=4)
z = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [0.5, 1.5, 2.5, 3.5]
], dtype=np.float32)

ARGS = {
    "z": z
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 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
unwrap Ran
ran; our contract draft was wrong, not the code
yk7333/DRND/online/envs.py
code served (permissive licence) · get_code("f2e3732f89410bea")
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 SimpleEnv. 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.

class SimpleEnv:
    def __init__(self):
        pass

class WrappedEnvWithUnwrapped:
    def __init__(self, base_env):
        self.unwrapped = base_env

class WrappedEnvWithEnv:
    def __init__(self, base_env):
        self.env = base_env

class WrappedEnvWithLegEnv:
    def __init__(self, base_env):
        self.leg_env = base_env

# Create a simple base environment
base_env = SimpleEnv()

# Create test environments with different wrapping styles
env_with_unwrapped = WrappedEnvWithUnwrapped(base_env)

ARGS = {
    'env': env_with_unwrapped
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleEnv — a SimpleEnv output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleEnv 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
softmax 3 other papers
3 dated earlier
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
2203.15565 (2022-03)
Killing Two Birds with One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC
2308.04836 (2023-08)
Beyond Surprise: Improving Exploration Through Surprise Novelty
unwrap 2 other papers
2 dated earlier
2104.07495 (2021-04)
Curiosity-Driven Exploration via Latent Bayesian Surprise
2308.04836 (2023-08)
Beyond Surprise: Improving Exploration Through Surprise Novelty

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

Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been demonstrated to be effective in numerous environments, it often needs more discriminative power in bonus allocation. This paper highlights the "bonus inconsistency" issue within RND, pinpointing its primary limitation. To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND. DRND enhances the exploration process by distilling a distribution of random networks and implicitly incorporating pseudo counts to improve the precision of bonus allocation. This refinement encourages agents to engage in more extensive exploration. Our method effectively mitigates the inconsistency issue without introducing significant computational overhead. Both theoretical analysis and experimental results demonstrate the superiority of our approach over the original RND algorithm. Our method excels in challenging online exploration scenarios and effectively serves as an anti-exploration mechanism in D4RL offline tasks. Our code is publicly available at https://github.com/yk7333/DRND.

For agents

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

get_harvested_code_for_paper("2401.09750")
get_code_for_paper("2401.09750")
have("2401.09750")

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

curl https://syntology.ai/api/ran/2401.09750.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.09750.svg)](https://syntology.ai/paper/2401.09750)

Connect an agent — have() is free.