SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.05087 · ICLR · 2022

Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL

Furong Huang, Yanchao Sun, Ruijie Zheng, Yongyuan Liang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 4 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/2106.05087.json · badge: /api/ran/2106.05087.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
umd-huang-lab/paad_adv_rl canonical (classifier label)
classifier basis: classifier_2025
9 ran · 4 no recorded run
FunctionStatusWhere it lives
common_fgsm Ran
ran; our contract draft was wrong, not the code
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("a1c75c1d902ef7d5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

common_momentum_fgm Ran
ran; our contract draft was wrong, not the code
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("90d3059238cd3942")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

common_pgd Ran
ran; our contract draft was wrong, not the code
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("b37b0f21185a06e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

get_policy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/trainer_adv/a2c_pa_attacker.py
pointer only (licence: NONE) · get_code("bf1679c31b6bfadf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

noisy_pgd Ran
ran; our contract draft was wrong, not the code
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("295c953ae1aedc03")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

obs_dir_perturb_fgsm Ran
ran; our contract draft was wrong, not the code
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/trainer_adv/a2c_pa_attacker.py
pointer only (licence: NONE) · get_code("21db8c7539b82cae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

obs_dir_perturb_momentum Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/trainer_adv/a2c_pa_attacker.py
pointer only (licence: NONE) · get_code("4aac02bd3c5c658b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

reward2tensor Ran
ran, honoured the contract we drafted
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attack_robust/radial_train_attacker.py
pointer only (licence: NONE) · get_code("b1e1cdc58f3fa6f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

state2tensor Ran
ran; our contract draft was wrong, not the code
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attack_robust/radial_train_attacker.py
pointer only (licence: NONE) · get_code("6517e45afce28963")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

Attacker Not yet run
unverified (harvested, no recorded run)
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("942887ec27de2b72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

KL_Attack Not yet run
unverified (harvested, no recorded run)
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("b3ecb431fa1b4ac3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

Param Not yet run
unverified (harvested, no recorded run)
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attacker/attacker.py
pointer only (licence: NONE) · get_code("a6f05c07b53af7b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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.

get_action Not yet run
unverified (harvested, no recorded run)
umd-huang-lab/paad_adv_rl/code_atari/paad_rl/attack_robust/radial_train_attacker.py
pointer only (licence: NONE) · get_code("2e86d0eab58b3a7b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umd-huang-lab/paad_adv_rl 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.

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

Evaluating the worst-case performance of a reinforcement learning (RL) agent under the strongest/optimal adversarial perturbations on state observations (within some constraints) is crucial for understanding the robustness of RL agents. However, finding the optimal adversary is challenging, in terms of both whether we can find the optimal attack and how efficiently we can find it. Existing works on adversarial RL either use heuristics-based methods that may not find the strongest adversary, or directly train an RL-based adversary by treating the agent as a part of the environment, which can find the optimal adversary but may become intractable in a large state space. This paper introduces a novel attacking method to find the optimal attacks through collaboration between a designed function named "actor" and an RL-based learner named "director". The actor crafts state perturbations for a given policy perturbation direction, and the director learns to propose the best policy perturbation directions. Our proposed algorithm, PA-AD, is theoretically optimal and significantly more efficient than prior RL-based works in environments with large state spaces. Empirical results show that our proposed PA-AD universally outperforms state-of-the-art attacking methods in various Atari and MuJoCo environments. By applying PA-AD to adversarial training, we achieve state-of-the-art empirical robustness in multiple tasks under strong adversaries. The codebase is released at https://github.com/umd-huang-lab/paad adv rl.

For agents

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

get_harvested_code_for_paper("2106.05087")
get_code_for_paper("2106.05087")
have("2106.05087")

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

curl https://syntology.ai/api/ran/2106.05087.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.05087.svg)](https://syntology.ai/paper/2106.05087)

Connect an agent — have() is free.