SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.04050 · ICLR · 2024

Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations

Zizhan Zheng, Xiaolin Sun

arXiv · PDF · Open in the Atlas

Code that ran

14 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 12 failures of our instrument; 10 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/2403.04050.json · badge: /api/ran/2403.04050.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
SliencerX/Belief-enriched-robust-Q-learning canonical (classifier label)
classifier basis: census
12 ran · 9 no recorded run
sliencerx/belief-enriched-robust-q-learning canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
activation_bound Ran
ran; our contract draft was wrong, not the code
SliencerX/Belief-enriched-robust-Q-learning/models_wocar.py
pointer only (licence: NONE) · get_code("69017b3a991e0815")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

argparser Ran
ran; our contract draft was wrong, not the code
SliencerX/Belief-enriched-robust-Q-learning/argparser.py
pointer only (licence: NONE) · get_code("62000ff4e804fe8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

conv Ran
ran; our contract draft was wrong, not the code
sliencerx/belief-enriched-robust-q-learning/pfrnns/model.py
pointer only (licence: NONE) · get_code("d8851346794d5b25")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sliencerx/belief-enriched-robust-q-learning 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.

conv2d Ran
ran; our contract draft was wrong, not the code
SliencerX/Belief-enriched-robust-Q-learning/diffusion_distiller/unet_ddpm.py
pointer only (licence: NONE) · get_code("73c8d2526f595b71")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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
SliencerX/Belief-enriched-robust-Q-learning/attacks.py
pointer only (licence: NONE); the stored copy get_code serves, from trustworthy-ml-lab/robust_highutil_smoothed_drl, is 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, SliencerX/Belief-enriched-robust-Q-learning 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.

isfloat Ran
ran, violated the contract we drafted
SliencerX/Belief-enriched-robust-Q-learning/argparser.py
pointer only (licence: NONE) · get_code("2f8e524a282482b9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

isint Ran
ran, violated the contract we drafted
SliencerX/Belief-enriched-robust-Q-learning/argparser.py
pointer only (licence: NONE) · get_code("10119e52ad9b6cf6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

linear Ran
ran; our contract draft was wrong, not the code
SliencerX/Belief-enriched-robust-Q-learning/diffusion_distiller/unet_ddpm.py
pointer only (licence: NONE) · get_code("b9aebc971fbddb2e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

normalize_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SliencerX/Belief-enriched-robust-Q-learning/atari_utils.py
pointer only (licence: NONE) · get_code("c0731c6888d80b74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SliencerX/Belief-enriched-robust-Q-learning/attacks.py
pointer only (licence: NONE) · get_code("b04a1a19e73c0ebb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

process_frame Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SliencerX/Belief-enriched-robust-Q-learning/atari_utils.py
pointer only (licence: NONE) · get_code("3785859a782d59c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

random_belief Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sliencerx/belief-enriched-robust-q-learning/test_atari.py
pointer only (licence: NONE) · get_code("660f559cc77eb623")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sliencerx/belief-enriched-robust-q-learning 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.

variance_scaling_init_ Ran
ran; our contract draft was wrong, not the code
SliencerX/Belief-enriched-robust-Q-learning/diffusion_distiller/unet_ddpm.py
pointer only (licence: NONE) · get_code("264892ef469646de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

weighted_bound Ran
ran; our contract draft was wrong, not the code
SliencerX/Belief-enriched-robust-Q-learning/models_wocar.py
pointer only (licence: NONE) · get_code("eba320329ae9cb63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

Belief_model Not yet run
unverified (harvested, no recorded run)
sliencerx/belief-enriched-robust-q-learning/pfrnns/model.py
pointer only (licence: NONE) · get_code("ceb412b14159f122")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sliencerx/belief-enriched-robust-q-learning 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.

add_noise Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/data_utils.py
pointer only (licence: NONE) · get_code("8874fd053928cefe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

add_noise_gauss Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/data_utils.py
pointer only (licence: NONE) · get_code("7c9f13bc7ba9c460")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

atari_env Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/atari_utils.py
pointer only (licence: NONE) · get_code("acb3ad120884bed7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

gen_traj Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/data_utils.py
pointer only (licence: NONE) · get_code("80057eea63e12ab2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

worker_add Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/async_rb.py
pointer only (licence: NONE) · get_code("32cc364b718bc705")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

worker_add_belief Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/async_rb.py
pointer only (licence: NONE) · get_code("6c52378bcd295e24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

worker_sample Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/async_rb.py
pointer only (licence: NONE) · get_code("7593b9941ac42115")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

worker_seed Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/async_env.py
pointer only (licence: NONE) · get_code("006b972124ee4c79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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.

worker_step Not yet run
unverified (harvested, no recorded run)
SliencerX/Belief-enriched-robust-Q-learning/async_env.py
pointer only (licence: NONE) · get_code("23a2244f0a9ef7fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SliencerX/Belief-enriched-robust-Q-learning 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 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 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
activation_bound 5 other papers
4 dated earlier, 1 later
1907.09470 (2019-07)
Characterizing Attacks on Deep Reinforcement Learning
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
2111.06063 (2021-11)
On the Equivalence between Neural Network and Support Vector Machine
and 2 more not named here
isfloat 4 other papers
4 dated earlier
1712.07629 (2017-12)
SuperPoint: Self-Supervised Interest Point Detection and Description
2002.12920 (2020-02)
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
2008.06081 (2020-08)
Adversarial Training and Provable Robustness: A Tale of Two Objectives
and 1 more not named here
weighted_bound 4 other papers
3 dated earlier, 1 later
1907.09470 (2019-07)
Characterizing Attacks on Deep Reinforcement Learning
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
2402.02165 (2024-02)
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
and 1 more not named here
isint 2 other papers
2 dated earlier
2002.12920 (2020-02)
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
2008.06081 (2020-08)
Adversarial Training and Provable Robustness: A Tale of Two Objectives
argparser 1 other paper
1 dated earlier
2002.12920 (2020-02)
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
conv2d 1 other paper
1 dated earlier
2211.12500 (2022-11)
Person Image Synthesis via Denoising Diffusion Model
fgsm 1 other paper
1 later
2406.18062 (2024-06)
Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
linear 1 other paper
1 dated earlier
2211.12500 (2022-11)
Person Image Synthesis via Denoising Diffusion Model
variance_scaling_init_ 1 other paper
1 dated earlier
2211.12500 (2022-11)
Person Image Synthesis via Denoising Diffusion Model

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

Reinforcement learning (RL) has achieved phenomenal success in various domains. However, its data-driven nature also introduces new vulnerabilities that can be exploited by malicious opponents. Recent work shows that a well-trained RL agent can be easily manipulated by strategically perturbing its state observations at the test stage. Existing solutions either introduce a regularization term to improve the smoothness of the trained policy against perturbations or alternatively train the agent's policy and the attacker's policy. However, the former does not provide sufficient protection against strong attacks, while the latter is computationally prohibitive for large environments. In this work, we propose a new robust RL algorithm for deriving a pessimistic policy to safeguard against an agent's uncertainty about true states. This approach is further enhanced with belief state inference and diffusion-based state purification to reduce uncertainty. Empirical results show that our approach obtains superb performance under strong attacks and has a comparable training overhead with regularization-based methods. Our code is available at https://github.com/SliencerX/Belief-enriched-robust-Q-learning.

For agents

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

get_harvested_code_for_paper("2403.04050")
get_code_for_paper("2403.04050")
have("2403.04050")

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

curl https://syntology.ai/api/ran/2403.04050.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.04050.svg)](https://syntology.ai/paper/2403.04050)

Connect an agent — have() is free.