SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.12427 · NeurIPS · 2022

Towards Safe Reinforcement Learning with a Safety Editor Policy

Haonan Yu, Wei Xu, Haichao Zhang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 2 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2201.12427.json · badge: /api/ran/2201.12427.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
hnyu/safety-gym canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
convert Ran
ran on a synthesized input
hnyu/safety-gym/safety_gym/envs/world.py
pointer only (licence: MIT) · get_code("9a58a6bb8dccddd3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, hnyu/safety-gym, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

normalize Ran
ran, honoured the contract we drafted
hnyu/safety-gym/safety_gym/bench/bench_utils.py
pointer only (licence: MIT) · get_code("d7740644bf4b7de1")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, hnyu/safety-gym, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

quat2zalign Ran
ran, violated the contract we drafted
hnyu/safety-gym/safety_gym/envs/engine.py
pointer only (licence: MIT) · get_code("4ac8031d738ec401")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, hnyu/safety-gym, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

rot2quat Ran
ran on a synthesized input
hnyu/safety-gym/safety_gym/envs/world.py
pointer only (licence: MIT) · get_code("b8083402c3d64e26")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, hnyu/safety-gym, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

theta2vec Ran
ran, honoured the contract we drafted
hnyu/safety-gym/safety_gym/envs/engine.py
pointer only (licence: MIT) · get_code("39708d407531ef32")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, hnyu/safety-gym, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
normalize 4 other papers
4 later
2303.03339 (2023-03)
Reducing Safety Interventions in Provably Safe Reinforcement Learning
2306.00035 (2023-06)
ROSARL: Reward-Only Safe Reinforcement Learning
2311.02227 (2023-11)
State-Wise Safe Reinforcement Learning With Pixel Observations
and 1 more not named here
quat2zalign 3 other papers
3 later
2303.03339 (2023-03)
Reducing Safety Interventions in Provably Safe Reinforcement Learning
2311.02227 (2023-11)
State-Wise Safe Reinforcement Learning With Pixel Observations
2401.14758 (2024-01)
Off-Policy Primal-Dual Safe Reinforcement Learning
theta2vec 3 other papers
3 later
2303.03339 (2023-03)
Reducing Safety Interventions in Provably Safe Reinforcement Learning
2311.02227 (2023-11)
State-Wise Safe Reinforcement Learning With Pixel Observations
2401.14758 (2024-01)
Off-Policy Primal-Dual Safe Reinforcement Learning
convert 1 other paper
1 later
2303.03339 (2023-03)
Reducing Safety Interventions in Provably Safe Reinforcement Learning
rot2quat 1 other paper
1 later
2303.03339 (2023-03)
Reducing Safety Interventions in Provably Safe Reinforcement Learning

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

Figure 1: SEditor's framework with two policies utility maximizer (UM) and safety editor (SE). Given a state s, UM proposes a preliminary action â that aims at maximizing the utility reward. Then SE outputs an adjustment ∆a to it based on s and â itself, to ensure a low constraint violation rate. The action proposal â and edit ∆a are fed to an action editing function h that outputs a final action a to interact with the environment. Both UM and SE are stochastic policies modeled as neural networks and are trained via SGD.

For agents

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

get_harvested_code_for_paper("2201.12427")
get_code_for_paper("2201.12427")
have("2201.12427")

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

curl https://syntology.ai/api/ran/2201.12427.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.12427.svg)](https://syntology.ai/paper/2201.12427)

Connect an agent — have() is free.