Papers › Robust Deep Reinforcement Learning through Adversarial Loss

Robust Deep Reinforcement Learning through Adversarial Loss

5 Aug 2020NeurIPS 2021 12arXiv:2008.01976archive 2025-07-28

Tuomas Oikarinen, Wang Zhang, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng

Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs, which raises concerns about deploying such agents in the real world. To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against lₚ-norm bounded adversarial attacks. Our framework is compatible with popular deep reinforcement learning algorithms and we demonstrate its performance with deep Q-learning, A3C and PPO. We experiment on three deep RL benchmarks (Atari, MuJoCo and ProcGen) to show the effectiveness of our robust training algorithm. Our RADIAL-RL agents consistently outperform prior methods when tested against attacks of varying strength and are more computationally efficient to train. In addition, we propose a new evaluation method called Greedy Worst-Case Reward (GWC) to measure attack agnostic robustness of deep RL agents. We show that GWC can be evaluated efficiently and is a good estimate of the reward under the worst possible sequence of adversarial attacks. All code used for our experiments is available at https://github.com/tuomaso/radial_rl_v2.

PaperPDFConference PDFCodeCode 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 9 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 2 repositories, 8 ran (6 with no instrument failure; 2 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 8 samples that ran have no recorded date.

tuomaso/radial_rl officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 6 ran (1 instrument-failed) · 1 unverified report
tuomaso/radial_rl_v2 officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 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

9 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

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

Licence: 2 of the 9 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.

tuomaso/radial_rl official repository 7 samples, 6 ran (1 instrument-failed) · 1 unverified
activation_bound in 6 papers A3C/ibp.py ran Apache-2.0 (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
initial_bounds in 5 papers A3C/ibp.py ran · violated contract fingerprinted Apache-2.0 (permissive) · cfb1c3dd218b92f0 · report fixture: signature x0:Tensor/4/float, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
process_frame in 6 papers A3C/environment.py ran Apache-2.0 (permissive) · 23ff92a17dc4fd23 · report fixture: signature frame:ndarray/3/int, conf:dict/0/? · returned ndarray · level recorded 2026-09-24
read_config in 49 papers A3C/utils.py ran · our draft was wrong Apache-2.0 (permissive) · 4000c95fa330f2ce · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
record_game A3C/evaluate.py ran Apache-2.0 (permissive) · 081882af810c4967 · report fixture: signature curr_model:callable/0/?, env:SimpleEnv/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-25
weighted_bound in 6 papers A3C/ibp.py ran Apache-2.0 (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 A3C/environment.py unverified Apache-2.0 (permissive) · a225ca9d1701067e · report
tuomaso/radial_rl_v2 official repository 2 samples, 2 ran (1 instrument-failed) · 0 unverified
safe_mean in 10 papers Procgen/eval_procgen.py ran · honoured contract fingerprinted no licence file found · pointer only · 9e4158212d676038 · report fixture: signature xs:list/1/float · returned float64 · level recorded, date not recorded
rollout_one_step Procgen/train_procgen.py ran · our draft was wrong no licence file found · pointer only · 9e82818c554c73e8 · report fixture: signature agent:callable/0/?, env:MinimalEnv/0/?, obs:Tensor/2/float, steps:Tensor/1/int, env_max_steps:int/0/int · returned tuple · level recorded, date not recorded

Tasks

Adversarial AttackAtari GamesDeep Reinforcement LearningMuJoCoQ-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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