SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.18062 · ICML · 2024

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents

Sicun Gao, Tsui-Wei Weng, Chung-En Sun

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 1 violated it and 0 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/2406.18062.json · badge: /api/ran/2406.18062.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
trustworthy-ml-lab/robust_highutil_smoothed_drl canonical (classifier label)
classifier basis: classifier_2025
9 ran · 3 no recorded run
FunctionStatusWhere it lives
action_scheduler Ran
ran, violated the contract we drafted
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/train_denoiser.py
pointer only (licence: NONE) · get_code("e74f5b2a28ba8052")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

arctanh_rescale Ran
ran, honoured the contract we drafted
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("7700197c7cc5747d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

fgsm Ran
ran; our contract draft was wrong, not the code
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("85a898709da49405")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

pgd Ran
ran; our contract draft was wrong, not the code
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("5a2c00df265799e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

rand_attack Ran
ran; our contract draft was wrong, not the code
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("e271cea23daebf1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

sigma_scheduler Ran
ran, honoured the contract we drafted
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/train_denoiser.py
pointer only (licence: NONE) · get_code("6919817644c97093")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

tanh_rescale Ran
ran, honoured the contract we drafted
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("9eeb6bd6911481c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

to_one_hot Ran
ran, honoured the contract we drafted
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("488e5c100aa0a20b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

torch_arctanh Ran
ran, honoured the contract we drafted
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("6a1ba12807275000")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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.

attack Not yet run
unverified (harvested, no recorded run)
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("bf58e2c221ef74b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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. No invocation recorded.

compute_td_loss Not yet run
unverified (harvested, no recorded run)
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/train_denoiser.py
pointer only (licence: NONE) · get_code("681b6da6079555d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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. No invocation recorded.

cw Not yet run
unverified (harvested, no recorded run)
trustworthy-ml-lab/robust_highutil_smoothed_drl/SDQN/attacks.py
pointer only (licence: NONE) · get_code("f43cc787cc6c05de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, trustworthy-ml-lab/robust_highutil_smoothed_drl 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 11 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
fgsm
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2403.04050 (2024-03)
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations

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

Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee across standard RL benchmarks. Notably, our S-DQN and S-PPO agents not only significantly outperform existing smoothed agents by an average factor of 2.16× under the strongest attack, but also surpass previous robustly-trained agents by an average factor of 2.13×. This represents a significant leap forward in the field. Furthermore, we introduce Smoothed Attack, which is 1.89× more effective in decreasing the rewards of smoothed agents than existing adversarial attacks. Our code

For agents

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

get_harvested_code_for_paper("2406.18062")
get_code_for_paper("2406.18062")
have("2406.18062")

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

curl https://syntology.ai/api/ran/2406.18062.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.18062.svg)](https://syntology.ai/paper/2406.18062)

Connect an agent — have() is free.