Papers › Regret-Based Defense in Adversarial Reinforcement Learning

Regret-Based Defense in Adversarial Reinforcement Learning

14 Feb 2023arXiv:2302.06912archive 2025-07-28

Roman Belaire, Pradeep Varakantham, Thanh Nguyen, David Lo

Deep Reinforcement Learning (DRL) policies have been shown to be vulnerable to small adversarial noise in observations. Such adversarial noise can have disastrous consequences in safety-critical environments. For instance, a self-driving car receiving adversarially perturbed sensory observations about nearby signs (e.g., a stop sign physically altered to be perceived as a speed limit sign) or objects (e.g., cars altered to be recognized as trees) can be fatal. Existing approaches for making RL algorithms robust to an observation-perturbing adversary have focused on reactive approaches that iteratively improve against adversarial examples generated at each iteration. While such approaches have been shown to provide improvements over regular RL methods, they are reactive and can fare significantly worse if certain categories of adversarial examples are not generated during training. To that end, we pursue a more proactive approach that relies on directly optimizing a well-studied robustness measure, regret instead of expected value. We provide a principled approach that minimizes maximum regret over a "neighborhood" of observations to the received "observation". Our regret criterion can be used to modify existing value- and policy-based Deep RL methods. We demonstrate that our approaches provide a significant improvement in performance across a wide variety of benchmarks against leading approaches for robust Deep RL.

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 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (6 with no instrument failure; 4 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/robust-ccer officialmentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (4 instrument-failed) · 1 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

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
6ran
1unverified

Licence: 0 of the 11 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 romanbelaire/robust-ccer. “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/robust-ccer official repository 11 samples, 10 ran (4 instrument-failed) · 1 unverified
consolidate_experiment code_mujoco/ccer/cox/generator.py ran MIT (permissive) · 075dfe30db346a5d · report fixture: signature exp_csv:str/0/str, command_maker:callable/0/?, num_sess:int/0/int, delete_after:bool/0/bool, session_prefix:str/0/str · returned str · level recorded 2026-09-25
dict_product in 8 papers code_mujoco/ccer/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 code_mujoco/ccer/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 code_mujoco/ccer/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
has_tensorboard code_mujoco/ccer/cox/archive.py ran MIT (permissive) · cd38a29fe01f4be3 · report fixture: signature dirname:str/0/str · returned bool · level recorded 2026-09-25
iwt in 5 papers code_mujoco/ccer/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
pack_history code_mujoco/ccer/policy_gradients/models.py ran MIT (permissive) · 934a0a9624814d4e · report fixture: signature features:Tensor/2/float, not_dones:Tensor/1/float · returned PackedSequence · level recorded 2026-09-25
partialclass in 13 papers code_mujoco/ccer/policy_gradients/models.py ran · our draft was wrong MIT (permissive) · 61098cd5c9624563 · report fixture: signature cls:callable/0/?, args:tuple/1/int, kwds:dict/0/? · returned type · level recorded 2026-09-22
schema_from_dict code_mujoco/ccer/cox/store.py ran MIT (permissive) · cfbb5cb3d22968c8 · report fixture: signature d:dict/0/?, alternative:str/0/str · returned dict · level recorded 2026-09-25
unpack_history code_mujoco/ccer/policy_gradients/models.py ran MIT (permissive) · 0c2504cab96329f1 · report fixture: signature padded_pieces:Tensor/3/float, lengths:Tensor/1/int · returned Tensor · level recorded 2026-09-25
generate_experiments code_mujoco/ccer/cox/generator.py unverified MIT (permissive) · b0c1eddd4ae7590e · report

Tasks

Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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