Papers › Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning

7 Jun 2024arXiv:2406.04724archive 2025-07-28

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. For instance, a self-driving car could experience catastrophic consequences if its sensory inputs about traffic signs are manipulated by an adversary. The core challenge in such situations is that the true state of the environment becomes only partially observable due to these adversarial manipulations. Two key strategies have so far been employed in the literature; the first set of methods focuses on increasing the likelihood that nearby states--those close to the true state--share the same robust actions. The second set of approaches maximize the value for the worst possible true state within the range of adversarially perturbed observations. Although these approaches provide strong robustness against attacks, they tend to be either overly conservative or not generalizable. We hypothesize that the shortcomings of these approaches stem from their failure to explicitly account for partial observability. By making decisions that directly consider this partial knowledge of the true state, we believe it is possible to achieve a better balance between robustness and performance, particularly in adversarial settings. To achieve this, we introduce a novel objective called Adversarial Counterfactual Error (ACoE), which is defined on the beliefs about the underlying true state and naturally balances value optimization with robustness against adversarial attacks, and a theoretically-grounded, scalable surrogate objective Cumulative-ACoE (C-ACoE). Our empirical evaluations demonstrate that our method significantly outperforms current state-of-the-art approaches for addressing adversarial RL challenges, offering a promising direction for better DRL under adversarial conditions.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 10 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 10 samples that ran have no recorded date.

romanbelaire/acoe-robust-rl officialmentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
5ran · our draft was wrong
4ran
2unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

romanbelaire/acoe-robust-rl official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
get_alg_name get_best_pickle.py ran · our draft was wrong fingerprinted MIT (permissive) · 85bf3d86b586cab7 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
get_env_name in 5 papers get_best_pickle.py ran · our draft was wrong fingerprinted MIT (permissive) · 35a892ade6c313d2 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
umd-huang-lab/WocaR-RL found in paper text by Syntology 10 samples, 8 ran (3 instrument-failed) · 2 unverified
activation_bound in 6 papers WocaR-DQN/SA-DQN/models.py ran MIT (permissive) · 69017b3a991e0815 · report fixture: signature layer:callable/0/?, prev_upper:Tensor/2/float, prev_lower:Tensor/2/float · returned tuple · level recorded 2026-09-24
dict_product in 8 papers WocaR-PPO/src/utils.py ran · our draft was wrong MIT (permissive) · 35b6f17122388f57 · report fixture: signature d:dict/0/? · returned map · level recorded 2026-09-22
get_alg_name WocaR-PPO/src/get_best_pickle.py ran · our draft was wrong fingerprinted MIT (permissive) · aa0592ec6641ad10 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
initial_bounds in 5 papers WocaR-DQN/RA-DQN/ibp.py ran · violated contract fingerprinted MIT (permissive) · cfb1c3dd218b92f0 · report fixture: signature x0:Tensor/4/float, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
iwt in 5 papers WocaR-PPO/src/utils.py ran MIT (permissive) · 942706632c22fc44 · report fixture: signature start:int/0/int, end:int/0/int, interval:int/0/int, trials:int/0/int · returned list · level recorded 2026-09-24
process_frame in 6 papers WocaR-DQN/RA-DQN/environment.py ran MIT (permissive) · 23ff92a17dc4fd23 · report fixture: signature frame:ndarray/3/int, conf:dict/0/? · returned ndarray · level recorded 2026-09-24
read_config in 49 papers WocaR-DQN/RA-DQN/utils.py ran · our draft was wrong MIT (permissive) · 4000c95fa330f2ce · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
weighted_bound in 6 papers WocaR-DQN/SA-DQN/models.py ran MIT (permissive) · eba320329ae9cb63 · report fixture: signature layer:callable/0/?, prev_upper:Tensor/2/float, prev_lower:Tensor/2/float · returned tuple · level recorded 2026-09-24
atari_env WocaR-DQN/RA-DQN/environment.py unverified MIT (permissive) · 09c7359e9f493f7c · report
record_game WocaR-DQN/RA-DQN/evaluate.py unverified MIT (permissive) · 3a204c610b328628 · report

Tasks

Deep Reinforcement LearningReinforcement Learningreinforcement-learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections