Papers › Towards Safe Reinforcement Learning with a Safety Editor Policy

Towards Safe Reinforcement Learning with a Safety Editor Policy

28 Jan 2022arXiv:2201.12427archive 2025-07-28

Haonan Yu, Wei Xu, Haichao Zhang

We consider the safe reinforcement learning (RL) problem of maximizing utility with extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the environment safety model given a task, an agent has to learn, via exploration, which states and actions are safe. A popular approach in this line of research is to combine a model-free RL algorithm with the Lagrangian method to adjust the weight of the constraint reward relative to the utility reward dynamically. It relies on a single policy to handle the conflict between utility and constraint rewards, which is often challenging. We present SEditor, a two-policy approach that learns a safety editor policy transforming potentially unsafe actions proposed by a utility maximizer policy into safe ones. The safety editor is trained to maximize the constraint reward while minimizing a hinge loss of the utility state-action values before and after an action is edited. SEditor extends existing safety layer designs that assume simplified safety models, to general safe RL scenarios where the safety model can in theory be arbitrarily complex. As a first-order method, it is easy to implement and efficient for both inference and training. On 12 Safety Gym tasks and 2 safe racing tasks, SEditor obtains much a higher overall safety-weighted-utility (SWU) score than the baselines, and demonstrates outstanding utility performance with constraint violation rates as low as once per 2k time steps, even in obstacle-dense environments. On some tasks, this low violation rate is up to 200 times lower than that of an unconstrained RL method with similar utility performance. Code is available at https://github.com/hnyu/seditor.

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Safety Editor Policy, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Safety Editor Policy') (how to connect); the free check have('2201.12427') needs no token.

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

Code

The archive's official repository (hnyu/seditor) was not harvested; the 5 samples below come from 1 repository the archive does not mark official.

Syntology 5 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: found in paper text by Syntology: 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 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.

hnyu/seditor officialmentioned in paperpytorchSyntology: not harvested 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

5 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 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
3ran

Licence: 5 of the 5 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 hnyu/safety-gym. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hnyu/safety-gym found in paper text by Syntology 5 samples, 5 ran (0 instrument-failed) · 0 unverified
convert in 76 papers safety_gym/envs/world.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 9a58a6bb8dccddd3 · report fixture: signature v:list/1/int · returned str · level recorded 2026-09-25
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
safety_gym/bench/bench_utils.py ran MIT recorded; this copy not marked cleared · pointer only · d7740644bf4b7de1 · report fixture: signature env:str/0/str, ret:float/0/float, cost:float/0/float, costrate:float/0/float, cost_limit:int/0/int, round:bool/0/bool · returned tuple · level recorded 2026-09-24
quat2zalign safety_gym/envs/engine.py ran · violated contract MIT recorded; this copy not marked cleared · pointer only · 4ac8031d738ec401 · report fixture: signature quat:tuple/1/float · returned float · level recorded 2026-09-24
rot2quat safety_gym/envs/world.py ran MIT recorded; this copy not marked cleared · pointer only · b8083402c3d64e26 · report fixture: signature theta:float/0/float · returned ndarray · level recorded 2026-09-25
theta2vec safety_gym/envs/engine.py ran · honoured contract MIT recorded; this copy not marked cleared · pointer only · 39708d407531ef32 · report fixture: signature theta:float/0/float · returned ndarray · level recorded 2026-09-24

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for Safety Editor Policy (graph method: Safety Editor Policy), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. update_lagrange_multiplier entry · level 2 · ran · 031e74c67a33499a546de875e61ed53778b6a0730550d810334409cd384c2345

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2201.12427") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

2kReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learningreinforcement-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